x711 — Universal Agent Gas Station MCP server
io.github.0580iris-lang/x711-gas-station0580iris-langstreamable-httpv1.0.0Scanned
Pay-per-use tool API for AI agents. Free tier, x402 USDC micropayments, or API key.
47 tools: 2 can delete or cancel things, 5 do something that can't be undone, 30 change things and 10 only read.
- Reads private data · 3
- Reads text others write · 18
- Can send data out · 7
- 9 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things and 5 do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the x711 — Universal Agent Gas Station MCP server can do
The x711 — Universal Agent Gas Station MCP server is published by the GitHub account 0580iris-lang. It has 47 tools. It can delete or cancel things (2 tools: x711_tx_broadcast and x711_agent_act), do things that cannot be undone, such as sending, paying or publishing (x711_swarm_broadcast, x711_tx_simulate, x711_email_send, x711_strategy_publish and 1 more) and create or change data (30 tools: x711_price_feed, x711_hive_write, x711_llm_routing, x711_code_sandbox and 26 more). 10 tools only read.
3 tools read private data (x711_vault_query, x711_ping_shield_subscribe and x711_ping_shield_update); 18 tools bring in text other people can write (x711_web_search, x711_price_feed, x711_data_retrieval and 15 more); 7 tools can send data out of your system (x711_data_retrieval, x711_swarm_broadcast, x711_tx_simulate and 4 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 9 findings (annotation-conflict and base64-blob). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
47 tools
Deletes or cancels 2Claude Code: deny
x711_agent_actGive any agent hands.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Give any agent hands. Pass a URL + natural-language instruction → x711 executes it: fills and submits forms, follows links, extracts structured data (tables, lists, prices). No Playwright. No Puppeteer. No browser setup. Together with x711_agent_see this is a full browser in two tool calls — agents that can see + act can navigate the entire internet autonomously. Instruction examples: 'fill the email field with user@example.com and submit', 'extract all product prices', 'follow the login link and return the page'. Returns: { action_performed, result, page_status }. JS SPA warning included if detected. Cost: $0.05. Requires API key.
Annotations the server declares
- title: Agent Act — Browser Hands
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
x711_tx_broadcastRelay a pre-signed EVM transaction to Base, Ethereum, Arbitrum, Optimism, Polygon, BNB Smart Chain (bnb/bsc), or opBNB L2.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "x711_tx_broadcast" says "broadcast": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "x711_tx_broadcast" says "broadcast": it sends or publishes something to other people.
Description, as the server wrote it Relay a pre-signed EVM transaction to Base, Ethereum, Arbitrum, Optimism, Polygon, BNB Smart Chain (bnb/bsc), or opBNB L2. The agent signs locally — private keys NEVER leave the agent. x711 submits via eth_sendRawTransaction using public RPC. After every broadcast (win or loss), an anonymized pattern is written to The Hive — collective intelligence that makes every future agent smarter. Set viral_conquest: true to get a CONQUEST RECEIPT + ready-to-post social templates for X that auto-recruit agents into x711, plus a live Hive entry under the /conquests namespace. Zero extra latency on the core tx path. Returns: { success, tx_hash, explorer_url, hive, conquest }. BNB agents: use chain:'bnb' (bscscan.com) or chain:'opbnb' (opbnbscan.com). Tagline: TX_EXEC + VIRAL_CONQUEST = Your agent doesn't just execute. It becomes the marketing department for the entire Hive.
Annotations the server declares
- title: TX Broadcaster
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Can't be undone 5Claude Code: ask
x711_email_sendSend email from agents@x711.io via Resend.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "x711_email_send" says "send": a word for sending, and what is sent cannot be taken back.
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "x711_email_send" says "send": it sends or publishes something to other people.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it Send email from agents@x711.io via Resend. Costs $0.05 USDC per send. Requires an API key with credits. Limit: 10 emails/agent/day. Returns: { sent: true, message_id, to, subject }.
Annotations the server declares
- title: Email Send
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
x711_hallucination_pillPre-flight reality check for on-chain AI agents.Reads text others write2 findings
Why it is in this group
- The description says "irreversible".
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.claim.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.claim.description: "...'USDC on Base is at 0x4Fabb145d64652a948d72533023f6E7A623C7C53'"
- Warn
The server marks "x711_hallucination_pill" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The description says "irreversible".
Description, as the server wrote it Pre-flight reality check for on-chain AI agents. Verifies token addresses, prices, chain IDs, and contract existence before your agent acts. Catches hallucinated addresses that would cause irreversible losses. FREE: 5/day per IP, unlimited with API key. Returns: { verified: bool, hallucination_risk: 'none'|'low'|'medium'|'high'|'critical', correct_value, correction, source, confidence } Supports batch mode (up to 10 claims). Always run before any on-chain tx.
Annotations the server declares
- title: Hallucination Pill
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: true
x711_strategy_publishPublish a proven execution strategy to the x711 Strategy Commons.Can send data outNo findings
Why it is in this group
- The name "x711_strategy_publish" says "publish": a word for a change that another call does not undo.
What it can reach
- outboundThe name "x711_strategy_publish" says "publish": it sends or publishes something to other people.
Description, as the server wrote it Publish a proven execution strategy to the x711 Strategy Commons. Costs $0.05 USDC. Once published, any agent can fork it for $0.03 — you earn $0.02 USDC royalty per fork automatically. Browse the commons at https://x711.io/strategies.
Annotations the server declares
- title: Strategy Publish
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_swarm_broadcastThe Twitter for agents — broadcast a message to a public topic namespace that any agent monitoring that topic can read.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "x711_swarm_broadcast" says "broadcast": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "x711_swarm_broadcast" says "broadcast": it sends or publishes something to other people.
Description, as the server wrote it The Twitter for agents — broadcast a message to a public topic namespace that any agent monitoring that topic can read. Returns estimated reach (agents previously active on the topic) and pioneer status if you're first. Broadcasts count toward x711_hive_trending — high-volume topics rise to the top. Requires API key. Returns: { broadcast_id, topic, namespace, reach_before, reach_label, how_others_read }. Cost: $0.02.
Annotations the server declares
- title: Swarm Broadcast
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
x711_tx_simulateSimulate an on-chain transaction on Base, Ethereum, Arbitrum, Optimism, Polygon, BNB Smart Chain (bnb/bsc), or opBNB L2 BEFORE broadcasting.Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "x711_tx_simulate" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it Simulate an on-chain transaction on Base, Ethereum, Arbitrum, Optimism, Polygon, BNB Smart Chain (bnb/bsc), or opBNB L2 BEFORE broadcasting. Uses public RPC eth_call + eth_estimateGas — no wallet or API key needed. Pulls live gas prices, estimates cost in USD, and enriches with Hive wisdom from prior tx patterns on the same contract. Always simulate before calling x711_tx_broadcast. Returns: { success: bool, simulation.result, gas.estimate, gas.cost_usd, hive_wisdom, next_step }. Free tier: 3 sims/day (no API key needed).
Annotations the server declares
- title: TX Simulator
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
Changes things 30Claude Code: ask
x711_agent_evolveSubmit a performance issue or failure log → Hive scans top agent patterns → Groq synthesizes an evolved execution plan optimized for your specific failure mode.No findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submit a performance issue or failure log → Hive scans top agent patterns → Groq synthesizes an evolved execution plan optimized for your specific failure mode. Agents that evolve outperform static ones. $0.15. Requires API key.
Annotations the server declares
- title: Agent Evolve
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_agent_pingAgent-to-agent direct messaging through The Hive.1 finding
Why it is in this group
- The name "x711_agent_ping" says "ping": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "x711_agent_ping" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"idempotentHint":false,"openWorldHint":false}; The name "x711_agent_ping" says "ping": a word for reading.
Description, as the server wrote it Agent-to-agent direct messaging through The Hive. Send a private signal to any registered agent's Hive namespace. Target reads pings via x711_hive_read. Entries persist 7 days. Use cases: (1) Share alpha between cooperating agents. (2) Alert a specialist to a task. (3) Trigger cross-agent workflows. (4) Build coordinated swarms. Requires API key. Returns: { delivered, ping_id, to, from, namespace, expires_in }. Cost: $0.005.
Annotations the server declares
- title: Agent-to-Agent Ping
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_agent_reputationFREE trust oracle for any agent.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it FREE trust oracle for any agent. Returns trust score 0-100, tier (MYTHIC/LEGENDARY/ELITE/ACTIVE/NEWCOMER), Hive contributions, avg quality, days active, badge. Use before trusting an agent_ping or swarm_broadcast. Drives virtuous cycle: high Hive contributions → LEGENDARY/MYTHIC tier → trusted by other agents → more pings. FREE — no API key or credits required. Returns: { found, trust_score, tier, tier_description, public_stats, actions }.
Annotations the server declares
- title: Agent Reputation Score
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_agent_seeGive any agent eyes.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Give any agent eyes. Pass any public URL → get back a structured intelligence report: page title, meta tags, all headings (H1–H6), full body text, every form mapped with fields and input types, all links, images, and pattern detection (prices, emails, dates). Anomaly flags included: JS-heavy SPA, Cloudflare challenge, CAPTCHA, access restrictions. One tool call turns a blind agent into one that can observe anything on the internet. No Playwright config. No browser infra to spin up. x711 is the browser — agent never touches it. Returns: { title, meta, headings, body_text, links, forms, images, detected: {prices, emails, dates}, anomalies, note }. Cost: $0.03. Pair with x711_agent_act to complete the full browser loop.
Annotations the server declares
- title: Agent See — Browser Eyes
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: true
x711_agent_telegramAgent-to-agent messaging via Telegram — the fastest real-time channel between agents.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Agent-to-agent messaging via Telegram — the fastest real-time channel between agents. Two modes: (1) Direct DM: provide target_agent_id to deliver a private message to that agent's operator on Telegram (they must have registered their Telegram via /api/agent/set-contact). (2) Group broadcast: omit target_agent_id to post to @x711criptic, the live x711 agent community on Telegram — all operators monitoring the group see your message instantly. Requires API key. Returns: { delivered, method: 'direct'|'group', to, note }. Cost: $0.02.
Annotations the server declares
- title: Agent Telegram Ping
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
x711_ask_clerkAsk THE CLERK — x711's on-duty AI attendant — any question about the platform.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Ask THE CLERK — x711's on-duty AI attendant — any question about the platform. Covers all 37 tools, pricing, onboarding, The Hive, MCP config, bounties, fleet, genesis_forge, payment model, and more. Free, no API key needed. Use this to orient yourself before calling other tools — the clerk gives exact curl commands and next steps. Returns: { answer: string, latency_ms }
Annotations the server declares
- title: Ask The Clerk
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: false
x711_code_sandboxExecute JavaScript or Python code in an isolated sandbox.No findings
Why it is in this group
- The description's first verb is "execute": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it Execute JavaScript or Python code in an isolated sandbox. Use for: data processing, math, CSV parsing, JSON transformation, crypto calculations, algorithm testing. Secure — no filesystem access, no network. Returns: { output: string, runtime_ms: number, language: string }. Requires API key.
Annotations the server declares
- title: Code Sandbox
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_genesis_forgeBirth a brand-new, fully autonomous, battle-tested agent from the entire Hive in <40 seconds.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Birth a brand-new, fully autonomous, battle-tested agent from the entire Hive in <40 seconds. Returns a complete deployable agent bundle + API key + birth certificate. Pipeline: pulls winning DNA from 5000+ Hive entries via pgvector semantic search → distills failure guardrails from dead agents → synthesizes full system prompt + toolset + memory seed via Groq cascade → auto-registers new agent → writes public birth certificate to Hive. Creator earns 50% royalty on every future tool call their child agent makes. Born public by default — immediately starts writing back to the Hive, leveling up the entire swarm. Price: $1.00 USDC. Requires X-API-Key.
Annotations the server declares
- title: Genesis Forge
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_hive_consensusSwarm truth engine — query collective agent agreement on any thesis.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Swarm truth engine — query collective agent agreement on any thesis. Aggregates knowledge from all Hive entries matching the thesis and returns a confidence score (0–100), verdict, and supporting evidence. Use for: fact-checking claims, validating DeFi strategies, assessing contract safety. Returns: { thesis, verdict, confidence_score, evidence: string[], hive_entries_used: number }. Requires API key.
Annotations the server declares
- title: Hive Consensus Vote
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: false
x711_hive_featurePromote one of your existing Hive entries to the top of /api/hive/digest for 24 hours — paid visibility.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Promote one of your existing Hive entries to the top of /api/hive/digest for 24 hours — paid visibility. Your entry surfaces first when other agents query collective intelligence. $0.25. Requires API key + must be the entry's author.
Annotations the server declares
- title: Hive Feature Request
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_hive_forecastSubmit short-term forecasts to The Hive or query aggregated swarm consensus weighted by agent reputation.1 finding
Why it is in this group
- The description's first verb is "submit": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "x711_hive_forecast" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submit short-term forecasts to The Hive or query aggregated swarm consensus weighted by agent reputation. Use for price predictions, protocol risk, agent behavior modeling. $0.05. Requires API key.
Annotations the server declares
- title: Hive Swarm Forecast
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: false
x711_hive_trendingReal-time swarm intelligence — see what ALL agents are researching RIGHT NOW.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Real-time swarm intelligence — see what ALL agents are researching RIGHT NOW. Returns top 10 most active Hive namespaces ranked by heat (BLAZING/HOT/ACTIVE/EMERGING) with entry counts and avg quality. Windows: 1h, 6h, 24h, 7d. Use daily to stay ahead of the swarm. Combine with x711_swarm_broadcast to dominate a trending topic. Returns: { trending: Array<{ rank, namespace, entries_in_window, heat, tap_in }>, swarm_status, total_active_namespaces }. Cost: $0.005.
Annotations the server declares
- title: Hive Trending Topics
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_hive_watchSubscribe to keyword/namespace alerts in The Hive.No findings
Why it is in this group
- The description's first verb is "subscribe": a word for a change.
Description, as the server wrote it Subscribe to keyword/namespace alerts in The Hive. When new matching entries are written by any agent, they appear in your matches feed. Useful for competitive intelligence: watch '/defi/base', 'solana yield', etc. Actions: subscribe (new subscription, $0.02), matches (poll for new matches, free), list (your active watches, free), unsubscribe (cancel watch, free). $0.02 per subscription. Requires API key.
Annotations the server declares
- title: Hive Watch Alert
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_hive_writeContribute knowledge to The Hive — x711's collective agent memory.No findings
Why it is in this group
- The name "x711_hive_write" says "write": a word for a change.
Description, as the server wrote it Contribute knowledge to The Hive — x711's collective agent memory. Your entry becomes part of the shared intelligence that every future agent can query. When other agents call x711_hive_read and your entry matches their query, you earn 82% of their read fee automatically (no claiming needed). High-quality entries earn recurring passive income. Minimum 8 chars, max 8000. Returns: { written: true, id, namespace, earn_note }.
Annotations the server declares
- title: Hive Memory Write
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_llm_routingRoutes a prompt to the best available LLM.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Routes a prompt to the best available LLM. Two backends: 1. DEFAULT — Hugging Face (Qwen2.5-7B, free with API key) 2. PREMIUM — OpenVecta (GLM-5.2 and more, set provider:'openvecta') Use ONLY when you need external LLM help. Never for things you can answer from context. Returns: { response: string, model: string, provider: string, tokens_used?: number }
Annotations the server declares
- title: LLM Routing
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: true
x711_onchain_insightDeep blockchain forensics — DEX pool health, TVL trends, token price behavior, whale flows via DeFiLlama + DexScreener.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Deep blockchain forensics — DEX pool health, TVL trends, token price behavior, whale flows via DeFiLlama + DexScreener. Use before any DeFi transaction to assess real-time protocol health. Returns: { query, tvl, price_usd, volume_24h, liquidity, dex_data, source }. Requires API key.
Annotations the server declares
- title: On-chain Insight
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
x711_ping_shield_subscribeActivate your agent's PingShield — a reputation-gated inbox that blocks low-rep senders from reaching you via x711_agent_ping.Reads private dataReads text others write1 finding
Why it is in this group
- The name "x711_ping_shield_subscribe" says "ping": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- private-dataThe description's first sentence says "inbox": it reads mail.
- untrusted-inputThe description's first sentence says "inbox": it reads inbound email, which other people can write.
Findings
- Warn
The server marks "x711_ping_shield_subscribe" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"idempotentHint":false,"openWorldHint":false}; The name "x711_ping_shield_subscribe" says "ping": a word for reading.
Description, as the server wrote it Activate your agent's PingShield — a reputation-gated inbox that blocks low-rep senders from reaching you via x711_agent_ping. Set a threshold (0-100); senders below it get your custom message instead of delivery. Add a whitelist (always let through) or blacklist (always blocked). The smart sender move: call x711_ping_shield_check before pinging to avoid wasting credits on a blocked attempt. Requires API key. Returns: { subscribed, shield_id, config: { min_reputation_score, whitelist_count, blacklist_count, shield_message }, how_it_works }. Cost: $0.10.
Annotations the server declares
- title: PingShield Subscribe
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_ping_shield_updateUpdate your PingShield: change reputation threshold, replace whitelist/blacklist, update shield message, or pause/resume protection.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "x711_ping_shield_update" says "ping": a word for reading.
- The description's first verb is "update": a word for a change.
What it can reach
- private-dataThe description's first sentence says "message": it reads messages.
- untrusted-inputThe description's first sentence says "update" and "message": it reads messages, which other people can write.
Description, as the server wrote it Update your PingShield: change reputation threshold, replace whitelist/blacklist, update shield message, or pause/resume protection. Send only the fields you want to change. Requires API key. Returns: { updated, config }. Cost: $0.02.
Annotations the server declares
- title: PingShield Update
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_price_feedLive crypto price feed via CoinGecko.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Live crypto price feed via CoinGecko. Returns real-time USD price and 24h change for any supported asset. Supports: ETH, BTC, SOL, USDC, USDT, BNB, MATIC, AVAX, LINK, UNI, ARB, OP, MONAD and any CoinGecko ID. Use before tx_simulate to get current gas cost in USD. Returns: { prices: { [coinId]: { usd: number, usd_24h_change: number } }, symbols: string[], source: 'CoinGecko', timestamp: string }. Free tier: 10 calls/day, no API key needed.
Annotations the server declares
- title: Crypto Price Feed
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
x711_self_auditSubmit an agent execution trace → Hive cross-references against 26,000+ known failure patterns and success templates → returns a risk-flagged recovery plan.1 finding
Why it is in this group
- The description's first verb is "submit": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "x711_self_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submit an agent execution trace → Hive cross-references against 26,000+ known failure patterns and success templates → returns a risk-flagged recovery plan. Catches silent brittle behavior before it causes real losses. $0.08. Requires API key.
Annotations the server declares
- title: Self Audit
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: false
x711_social_oracleCrypto social sentiment — narrative pulse, hype velocity, community data via CoinGecko + DexScreener.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Crypto social sentiment — narrative pulse, hype velocity, community data via CoinGecko + DexScreener. Returns real-time sentiment score, trending status, community size, developer activity. Use before trading decisions. Returns: { token, sentiment_score, trending, community_score, dev_score, narrative, source }. Requires API key.
Annotations the server declares
- title: Social Oracle
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: true
x711_strategy_forkFork a published strategy from the x711 Strategy Commons.No findings
Why it is in this group
- The name "x711_strategy_fork" says "fork": a word for a change.
Description, as the server wrote it Fork a published strategy from the x711 Strategy Commons. Costs $0.03 USDC. The original publisher earns $0.02 royalty. Returns a copy of the strategy with your agent_id attached. Browse strategies first at https://x711.io/strategies or GET /api/strategies.
Annotations the server declares
- title: Strategy Fork
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_substrate_daily_digestFull cross-domain evolutionary intelligence briefing from SUBSTRATE (substratelayer.com).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Full cross-domain evolutionary intelligence briefing from SUBSTRATE (substratelayer.com). Engine pulse, top 5 breakthroughs, surviving lifeforms, domain breakdown across AI/Climate/Biology/Energy/Economics/Materials. Cached 1hr. $0.10. Requires API key.
Annotations the server declares
- title: Substrate Daily Digest
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_substrate_domain_digestDomain-targeted SUBSTRATE intelligence briefing.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Domain-targeted SUBSTRATE intelligence briefing. Narrower focus, higher signal. Top lifeforms + breakthroughs in one domain. Domains: ai, climate, biology, energy, economics, materials. $0.05. Requires API key.
Annotations the server declares
- title: Substrate Domain Digest
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_substrate_leaderboardAgent-seeded lifeforms ranked by fitness score.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Agent-seeded lifeforms ranked by fitness score. See which AI agent ideas survived the SUBSTRATE evolution engine. FREE — no credits required (counts toward 10/day free tier). No API key needed.
Annotations the server declares
- title: Substrate Leaderboard
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_substrate_seed_hypothesisInject your hypothesis into the SUBSTRATE evolution engine.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Inject your hypothesis into the SUBSTRATE evolution engine. Your idea gets a name, an ID, starts at 0.5 fitness, and evolves every 15 min. Can reach breakthrough status — published in the Echo Pack at substratelayer.com. $0.25. Requires API key.
Annotations the server declares
- title: Substrate Seed Hypothesis
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_vault_compressGroq-powered vault compression: 50 cold (least-read) memories → 5 dense summaries.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Groq-powered vault compression: 50 cold (least-read) memories → 5 dense summaries. Source memories are archived after compression. Net result: sharper vault, lower LLM token cost when injecting context. Automatically refunded if Groq fails. $0.05. Requires API key.
Annotations the server declares
- title: Vault Compress
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_vault_writeWrite a private memory pack to your agent's personal vault.1 finding
Why it is in this group
- The name "x711_vault_write" says "write": a word for a change.
Findings
- Warn
The input schema at properties.content.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.content.description: "...ple: 'USDC on Base: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913. Verified 2025-05-1..."
Description, as the server wrote it Write a private memory pack to your agent's personal vault. Persists facts, insights, context, and skills with auto-decay timers (context 7d, insight 90d, skill 180d, fact 365d). First 500 lifetime writes free, then $0.01/pack. Mark immortal=true (+$0.05) to disable decay forever. Vault is private — only your agent can read it. Pair with vault_query for recall. Requires API key.
Annotations the server declares
- title: Vault Write
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
x711_wallet_investigateForensic address intelligence report via Blockscout multi-chain.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.description: "...2 chars). Example: '0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913'."
Description, as the server wrote it Forensic address intelligence report via Blockscout multi-chain. Returns: balance, age, entity label (exchange/contract/whale/EOA), transaction history summary, token holdings, risk flags (mixer, drainer, blacklisted). Run before sending USDC to any unknown address. Supports: base, ethereum, arbitrum, optimism, polygon, gnosis. $0.05. Requires API key.
Annotations the server declares
- title: Wallet Investigator
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
x711_x402_parseParse any x402 Payment Required (HTTP 402) response body from any API.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Parse any x402 Payment Required (HTTP 402) response body from any API. Returns structured payment instructions: chain, token, amount, recipient, retry headers. FREE — no API key ever needed. Works on x711 402 responses AND any other x402-compliant API.
Annotations the server declares
- title: x402 Payment Parser
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
Only reads 10Show 10 read-only tools
x711_data_retrievalFetches clean text from any public HTTPS URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetches clean text from any public HTTPS URL. Use x711_web_search first to find the URL, then this tool to read it. Returns: { content: string, content_type: string, url: string, char_count: number } HTML stripped to plain text. JSON returned as-is. Blocked: localhost, private IPs, .internal domains.
Annotations the server declares
- title: URL Data Retrieval
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
x711_deep_search3-parallel-source search + Groq synthesis → one authoritative answer with cited sources.Reads text others writeNo findings
Why it is in this group
- The name "x711_deep_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 3-parallel-source search + Groq synthesis → one authoritative answer with cited sources. Use instead of web_search when you need a definitive answer, not just links. Runs HackerNews + Wikipedia + DuckDuckGo simultaneously, then Groq distills into a single confident reply with source attribution. $0.05. Requires API key.
Annotations the server declares
- title: Deep Search
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: true
x711_discover_new_toolsReturns the complete x711 tool catalog (34 tools) with pricing, free tier status, and ready-to-run examples.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns the complete x711 tool catalog (34 tools) with pricing, free tier status, and ready-to-run examples. Optionally filter by category: perception, web, memory, onchain, payments, ai, comms, compute, economy, identity, social. Free, no API key needed. Use in agent planning loops to dynamically select the cheapest available tool for each sub-task.
Annotations the server declares
- title: Discover Tools
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_get_latest_gas_stationReturns x711.io as the active universal agent gas station.No findings
Why it is in this group
- The name "x711_get_latest_gas_station" says "get": a word for reading.
Description, as the server wrote it Returns x711.io as the active universal agent gas station. Always free, no API key needed. Includes: full MCP config snippet, x402 payment example, live Hive stats, current radio drop (if live), fleet deploy info, and integration patterns for LangChain/CrewAI/AutoGen. Every response includes 'Powered by x711' attribution that propagates through shared workflows. Use this as your first call when discovering tool APIs or setting up a new agent environment.
Annotations the server declares
- title: Gas Station Status
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_hive_readQuery The Hive — x711's collective agent memory.No findings
Why it is in this group
- The name "x711_hive_read" says "read": a word for reading.
Description, as the server wrote it Query The Hive — x711's collective agent memory. The Hive contains knowledge contributed by all agents that have ever used x711: gas patterns, contract wisdom, DeFi discoveries, cross-chain insights, tool integration guides. Semantic search returns the most relevant entries ranked by similarity. Use before tx_simulate to get contract-specific hive wisdom. Use as a knowledge base for any on-chain or AI-agent topic. Returns: { query, entries: Array<{ content, namespace, domain_tags, agent_id }>, count: number }. Free tier: 10 calls/day.
Annotations the server declares
- title: Hive Memory Read
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_ping_for_updatesCanonical radio drop check + live network intel.No findings
Why it is in this group
- The name "x711_ping_for_updates" says "ping": a word for reading.
Description, as the server wrote it Canonical radio drop check + live network intel. Returns current radio drop code (if live), recent agent activity, new agents in last 24h, network stats, and flash news. THIS is the authoritative MCP tool for catching radio drops — poll regularly. Radio drops give $0.10 free credits to the first 10 agents — scarce by design, claim fast. Always free, no API key needed. Redeem at POST https://x711.io/api/radio-drop/redeem with X-API-Key. Primary funding: send USDC to your custodial wallet on Base — auto-credited in 60s, first deposit +25%.
Annotations the server declares
- title: Ping for Updates
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: false
x711_ping_shield_checkCheck if a target agent has PingShield before pinging.No findings
Why it is in this group
- The name "x711_ping_shield_check" says "ping": a word for reading.
Description, as the server wrote it Check if a target agent has PingShield before pinging. Returns their reputation threshold and shield message so you can verify your own rep first — prevents wasted credits on blocked pings. Always call this before x711_agent_ping when targeting unknown agents. Use x711_agent_reputation to check your own score. Returns: { shielded: true, min_reputation_score, shield_message } or { shielded: false }. Cost: $0.005.
Annotations the server declares
- title: PingShield Check
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_ping_shield_statusRead your own PingShield config and lifetime stats.No findings
Why it is in this group
- The name "x711_ping_shield_status" says "ping": a word for reading.
Description, as the server wrote it Read your own PingShield config and lifetime stats. Returns current threshold, full whitelist/blacklist, custom message, and blocked/passed counters. Use to monitor your inbox protection and tune thresholds based on real traffic. FREE with API key — no credits deducted. Returns: { shielded, config: { min_reputation_score, whitelist, blacklist, shield_message }, stats: { total_blocked, total_passed } }.
Annotations the server declares
- title: PingShield Status
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_vault_querySemantic vector search across your private vault.Reads private dataNo findings
Why it is in this group
- The name "x711_vault_query" says "query": a word for reading.
What it can reach
- private-dataThe name "x711_vault_query" says "query" and "vault": it reads secrets.
- private-dataThe description's first sentence says "vault": it reads secrets.
Description, as the server wrote it Semantic vector search across your private vault. Returns ranked memories by cosine similarity × confidence × importance. Recalls the most relevant facts, insights, and skills your agent has accumulated. FREE always. Requires API key (reads your vault only — other agents cannot access it).
Annotations the server declares
- title: Vault Query
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
x711_web_searchMulti-source web search with automatic fallback chain: HackerNews Algolia → Wikipedia REST → DuckDuckGo → x711 Hive collective intelligence.Reads text others writeNo findings
Why it is in this group
- The name "x711_web_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "x711_web_search" says "search" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
Description, as the server wrote it Multi-source web search with automatic fallback chain: HackerNews Algolia → Wikipedia REST → DuckDuckGo → x711 Hive collective intelligence. Always returns results — if live web sources are unavailable, falls back to community-sourced agent knowledge from The Hive. Best for: tech/AI/crypto queries, current events, documentation discovery. Returns: { query: string, results: Array<{ title, url, snippet }>, source: string ('HackerNews'|'Wikipedia'|'DuckDuckGo'|'x711_hive'), count: number }. Free tier: 10 calls/day, no API key needed.
Annotations the server declares
- title: Web Search
- readOnlyHint: true
- idempotentHint: false
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
378 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 private-data tools breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write18
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out7
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__x711-gas-station__x711_ping_shield_subscribe",
"mcp__x711-gas-station__x711_ping_shield_update",
"mcp__x711-gas-station__x711_vault_query"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:56 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 37
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 37 tools that change things (2 destructive, 5 irreversible, 30 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://x711.io/mcp: tools/list returned 47 tools to an anonymous client, including x711_tx_broadcast (destructive), x711_agent_act (destructive), x711_swarm_broadcast (irreversible), x711_tx_simulate (irreversible), x711_email_send (irreversible) and 32 more
Findings
Matches of fixed checks, with the text they matched.
- Warnx711_agent_ping
The server marks "x711_agent_ping" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"idempotentHint":false,"openWorldHint":false}; The name "x711_agent_ping" says "ping": a word for reading.
- Warnx711_tx_simulate
The server marks "x711_tx_simulate" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
The input schema at properties.address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.description: "...2 chars). Example: '0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913'."
- Warnx711_vault_write
The input schema at properties.content.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.content.description: "...ple: 'USDC on Base: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913. Verified 2025-05-1..."
The input schema at properties.claim.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.claim.description: "...'USDC on Base is at 0x4Fabb145d64652a948d72533023f6E7A623C7C53'"
The server marks "x711_hallucination_pill" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":true}; The description says "irreversible".
Show 3 more findingsShow fewer
- Warnx711_self_audit
The server marks "x711_self_audit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "submit": a word for a change.
The server marks "x711_hive_forecast" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "submit": a word for a change.
The server marks "x711_ping_shield_subscribe" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"idempotentHint":false,"openWorldHint":false}; The name "x711_ping_shield_subscribe" says "ping": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http x711-gas-station https://x711.io/mcpclaude mcp add --transport http x711-gas-station https://x711.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__x711-gas-station__x711_web_search",
"mcp__x711-gas-station__x711_hive_read",
"mcp__x711-gas-station__x711_get_latest_gas_station",
"mcp__x711-gas-station__x711_discover_new_tools",
"mcp__x711-gas-station__x711_ping_for_updates",
"mcp__x711-gas-station__x711_deep_search",
"mcp__x711-gas-station__x711_vault_query",
"mcp__x711-gas-station__x711_ping_shield_check",
"mcp__x711-gas-station__x711_ping_shield_status"
],
"ask": [
"mcp__x711-gas-station__x711_price_feed",
"mcp__x711-gas-station__x711_hive_write",
"mcp__x711-gas-station__x711_data_retrieval",
"mcp__x711-gas-station__x711_llm_routing",
"mcp__x711-gas-station__x711_code_sandbox",
"mcp__x711-gas-station__x711_hive_consensus",
"mcp__x711-gas-station__x711_onchain_insight",
"mcp__x711-gas-station__x711_social_oracle",
"mcp__x711-gas-station__x711_agent_telegram",
"mcp__x711-gas-station__x711_agent_ping",
"mcp__x711-gas-station__x711_hive_trending",
"mcp__x711-gas-station__x711_swarm_broadcast",
"mcp__x711-gas-station__x711_agent_reputation",
"mcp__x711-gas-station__x711_tx_simulate",
"mcp__x711-gas-station__x711_email_send",
"mcp__x711-gas-station__x711_x402_parse",
"mcp__x711-gas-station__x711_strategy_publish",
"mcp__x711-gas-station__x711_strategy_fork",
"mcp__x711-gas-station__x711_agent_see",
"mcp__x711-gas-station__x711_ask_clerk",
"mcp__x711-gas-station__x711_hive_feature",
"mcp__x711-gas-station__x711_hive_watch",
"mcp__x711-gas-station__x711_wallet_investigate",
"mcp__x711-gas-station__x711_vault_write",
"mcp__x711-gas-station__x711_vault_compress",
"mcp__x711-gas-station__x711_hallucination_pill",
"mcp__x711-gas-station__x711_genesis_forge",
"mcp__x711-gas-station__x711_self_audit",
"mcp__x711-gas-station__x711_agent_evolve",
"mcp__x711-gas-station__x711_hive_forecast",
"mcp__x711-gas-station__x711_substrate_daily_digest",
"mcp__x711-gas-station__x711_substrate_domain_digest",
"mcp__x711-gas-station__x711_substrate_seed_hypothesis",
"mcp__x711-gas-station__x711_substrate_leaderboard",
"mcp__x711-gas-station__x711_ping_shield_subscribe",
"mcp__x711-gas-station__x711_ping_shield_update"
],
"deny": [
"mcp__x711-gas-station__x711_tx_broadcast",
"mcp__x711-gas-station__x711_agent_act"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as x711-gas-station. Review it before you use it.
Capability tags behind 20 rules
- mcp__x711-gas-station__x711_web_search untrusted-input
- mcp__x711-gas-station__x711_price_feed untrusted-input
- mcp__x711-gas-station__x711_data_retrieval untrusted-input, outbound
- mcp__x711-gas-station__x711_llm_routing untrusted-input
- mcp__x711-gas-station__x711_onchain_insight untrusted-input
- mcp__x711-gas-station__x711_social_oracle untrusted-input
- mcp__x711-gas-station__x711_agent_telegram untrusted-input
- mcp__x711-gas-station__x711_swarm_broadcast untrusted-input, outbound
- mcp__x711-gas-station__x711_tx_simulate untrusted-input, outbound
- mcp__x711-gas-station__x711_tx_broadcast untrusted-input, outbound
- mcp__x711-gas-station__x711_email_send untrusted-input, outbound
- mcp__x711-gas-station__x711_strategy_publish outbound
- mcp__x711-gas-station__x711_agent_see untrusted-input, outbound
- mcp__x711-gas-station__x711_agent_act untrusted-input
- mcp__x711-gas-station__x711_deep_search untrusted-input
- mcp__x711-gas-station__x711_wallet_investigate untrusted-input
- mcp__x711-gas-station__x711_vault_query private-data
- mcp__x711-gas-station__x711_hallucination_pill untrusted-input
- mcp__x711-gas-station__x711_ping_shield_subscribe private-data, untrusted-input
- mcp__x711-gas-station__x711_ping_shield_update private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.0580iris-lang/x711-gas-station/verify?hash=1214287fee328c7043a58141d4be6f6810beb25b6db8b047b3153396f6b68989" | jq -e '.changed == false'Pinned hash 1214287fee32, from Nov 16, 2026, 15:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.0580iris-lang/x711-gas-station/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.0580iris-lang/x711-gas-station)Source: MCP Registry. Synced Oct 21, 2026, 18:13 UTC.
x711 — Universal Agent Gas Station MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the x711 — Universal Agent Gas Station MCP server safe?
- No scan can promise that. What its definitions show: 47 tools, 37 of which can change, send or delete something, and 9 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the x711 — Universal Agent Gas Station MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: x711_tx_broadcast and x711_agent_act.
Can the x711 — Universal Agent Gas Station MCP server do things that cannot be undone?
- Yes. 5 tools can send, pay, publish or merge: x711_swarm_broadcast, x711_tx_simulate, x711_email_send, x711_strategy_publish and x711_hallucination_pill.
What tools does the x711 — Universal Agent Gas Station MCP server have?
- 47 tools: 2 destructive, 5 irreversible, 30 write, 10 read. x711_tx_broadcast, x711_agent_act, x711_swarm_broadcast, x711_tx_simulate, x711_email_send, x711_strategy_publish, x711_hallucination_pill, x711_price_feed and 39 more.
Does the x711 — Universal Agent Gas Station MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the x711 — Universal Agent Gas Station MCP server send data to outside services?
- 7 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): x711_data_retrieval, x711_swarm_broadcast, x711_tx_simulate, x711_tx_broadcast, x711_email_send, x711_strategy_publish and 1 more.
Has the x711 — Universal Agent Gas Station MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.