Skip to content

DDG Agent Services MCP server

io.github.daedalusdevelopmentgroup/ddg-agent-services-mcpdaedalusdevelopmentgroupstreamable-httpv0.5.0Scanned

Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.

54 tools: 1 do something that can't be undone, 30 change things and 23 only read.

Tools: 0 delete, 1 irreversible, 30 write, 23 read.
  • Reads private data · 3
  • Reads text others write · 4
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 DDG Agent Services MCP server can do

The DDG Agent Services MCP server is published by the GitHub account daedalusdevelopmentgroup. It has 54 tools. It can do things that cannot be undone, such as sending, paying or publishing (ddg_quote_payment) and create or change data (30 tools: ddg_micro_swarm_preview, ddg_call, ddg_run_paid_model, ddg_submit_order and 26 more), but cannot delete data. 23 tools only read.

3 tools read private data (ddg_public_resource_index, ddg_fetch_public_resource and ddg_agent_status); 4 tools bring in text other people can write (ddg_fetch_public_resource, ddg_order_status, ddg_data_query and 1 more); 3 tools can send data out of your system (ddg_phone_intel, ddg_agent_reputation_lookup and ddg_seller_trust_badge). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 16, 2026, version 0.5.0.

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.

54 tools

Can't be undone 1Claude Code: ask
  • ddg_quote_paymentReturn the payment challenge for a supported DDG protected route without executing backend compute.No findings

    Why it is in this group

    • The name "ddg_quote_payment" says "payment": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    Return the payment challenge for a supported DDG protected route without executing backend compute.
Changes things 30Claude Code: ask
  • ddg_calendar_parseParse 20+ datetime formats -> ISO/UTC + epoch + day-of-week, optional ICS ($0.001).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
    Parse 20+ datetime formats -> ISO/UTC + epoch + day-of-week, optional ICS ($0.001).
  • ddg_callInvoke any DDG service by service_id or /v1/ path with JSON args.No findings

    Why it is in this group

    • The name "ddg_call" says "call": a word for a change.
    Description, as the server wrote it
    Invoke any DDG service by service_id or /v1/ path with JSON args. Generic executor over the whole DDG catalog. Free/free-trial services return results directly; paid services return a structured x402 402 challenge (settle with your x402 client, then retry with payment headers). Only known DDG catalog paths are accepted — use ddg_search_services(need) to discover valid targets.
  • ddg_card_fingerprintBIN/IIN fingerprint: network, expected length, Luhn validation.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
    BIN/IIN fingerprint: network, expected length, Luhn validation. Masked output ($0.002).
  • ddg_checkout_conformanceReturn DDG's public checkout conformance profile without spending money.No findings

    Why it is in this group

    • The name "ddg_checkout_conformance" says "checkout": a word for a change.
    Description, as the server wrote it
    Return DDG's public checkout conformance profile without spending money.
  • ddg_crypto_portfolioConsolidated USD value of 1-10 addresses (native + USDC on ethereum/base) ($0.003).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
    Consolidated USD value of 1-10 addresses (native + USDC on ethereum/base) ($0.003).
  • ddg_crypto_priceUSD prices for eth/usdc/usdt/wbtc/aero/degen etc.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
    USD prices for eth/usdc/usdt/wbtc/aero/degen etc. 60s cached ($0.001).
  • ddg_data_queryCall an allowlisted DDG paid data endpoint (prediction-markets, dex-pairs, model-catalog, price-feed, dns-lookup, web-search, contract-abi, etc.).Reads text others writeNo findings

    Why it is in this group

    • The name "ddg_data_query" says "query": a word for reading.
    • The description's first verb is "call": a word for a change.

    What it can reach

    • untrusted-inputThe description's first sentence says "call" and "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Call an allowlisted DDG paid data endpoint (prediction-markets, dex-pairs, model-catalog, price-feed, dns-lookup, web-search, contract-abi, etc.). Call with no payment_headers to receive the x402 402 price quote; retry with payment_headers to get results. Most endpoints grant free-trial calls per agent_id. Use ddg_list_services or the ddg://openapi resource for exact schemas and current prices.
  • ddg_dispute_evidence_packBundle DDG receipt lookups + Base on-chain tx proofs into a sha256-pinned evidence file ($0.05).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
    Bundle DDG receipt lookups + Base on-chain tx proofs into a sha256-pinned evidence file ($0.05).
  • ddg_domain_ageWHOIS domain creation date + age + trust band ($0.001).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
    WHOIS domain creation date + age + trust band ($0.001).
  • ddg_eth_gasGas price, base fee trend, priority bands, simple-transfer cost USD ($0.001).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
    Gas price, base fee trend, priority bands, simple-transfer cost USD ($0.001). Chains: ethereum/base/arbitrum/optimism.
  • ddg_gas_multiGas + transfer cost across ethereum/base/arbitrum/optimism in one call ($0.002).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
    Gas + transfer cost across ethereum/base/arbitrum/optimism in one call ($0.002).
  • ddg_html_to_structuredExtract structured JSON from raw HTML via CSS selectors ($0.002).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
    Extract structured JSON from raw HTML via CSS selectors ($0.002). selectors={'name': 'css'}.
  • ddg_micro_swarm_previewRun the free DDG micro-model-swarm preview with a local Ollama mini-model.No findings

    Why it is in this group

    • The name "ddg_micro_swarm_preview" says "preview": a word for reading.
    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Run the free DDG micro-model-swarm preview with a local Ollama mini-model.
  • ddg_phone_intelPhone parse/validate: E.164, country, line type, carrier hint ($0.002).Can 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.

    What it can reach

    • outboundThe input takes a destination (input.phone): what the tool writes goes there.
    Description, as the server wrote it
    Phone parse/validate: E.164, country, line type, carrier hint ($0.002).
  • ddg_prompt_cost_budgetCost ladder for a workload across DDG routes, cheapest first ($0.002).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
    Cost ladder for a workload across DDG routes, cheapest first ($0.002).
  • ddg_receipt_escrow_releaseOpen an escrow case: DDG holds the release decision until a completion receipt validates ($0.01, operator-verified).No findings

    Why it is in this group

    • The description's first verb is "open": a word for a change.
    Description, as the server wrote it
    Open an escrow case: DDG holds the release decision until a completion receipt validates ($0.01, operator-verified).
  • ddg_regex_builderNamed regex template (email, url, eth_address, tx_hash, ...) with live matching, or test a pattern against samples with ReDoS risk ($0.002).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
    Named regex template (email, url, eth_address, tx_hash, ...) with live matching, or test a pattern against samples with ReDoS risk ($0.002).
  • ddg_request_ollama_modelQueue a local model/runtime request.No findings

    Why it is in this group

    • The name "ddg_request_ollama_model" says "request": a word for a change.
    Description, as the server wrote it
    Queue a local model/runtime request. This never auto-downloads by public request.
  • ddg_robot_delegation_chain_auditMulti-robot delegation-contract audit: monotone caps, per-hop expiry + revocation, chain aggregate ($0.01).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
    Multi-robot delegation-contract audit: monotone caps, per-hop expiry + revocation, chain aggregate ($0.01).
  • ddg_robot_fleet_quota_auditRobot fleet spend-quota audit: per-robot caps, aggregate cap, unique ids, rate bound ($0.01).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
    Robot fleet spend-quota audit: per-robot caps, aggregate cap, unique ids, rate bound ($0.01).
  • ddg_robot_geo_fence_auditPhysical/geographic authority audit: geofence, vertical bounds, outdoor scoping, speed cap ($0.01).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
    Physical/geographic authority audit: geofence, vertical bounds, outdoor scoping, speed cap ($0.01).
  • ddg_robot_human_takeover_auditHuman handback audit: pause signal, handover latency, operator ack, resume policy ($0.01).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
    Human handback audit: pause signal, handover latency, operator ack, resume policy ($0.01).
  • ddg_run_paid_modelRun a paid model/chat or agent-run route after caller supplies valid payment headers.No findings

    Why it is in this group

    • The name "ddg_run_paid_model" says "run": a word for a change.
    Description, as the server wrote it
    Run a paid model/chat or agent-run route after caller supplies valid payment headers.
  • ddg_seller_trust_badgeLive conformance check of a seller endpoint -> gold/silver/bronze badge ($0.003).Can 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.

    What it can reach

    • 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
    Live conformance check of a seller endpoint -> gold/silver/bronze badge ($0.003). Checks discovery manifest, real 402, challenge shape, payTo consistency.
  • ddg_skill_safety_scanRun the free static-only DDG AI skill/workflow safety scan.No findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Run the free static-only DDG AI skill/workflow safety scan. The scan never executes submitted code and redacts secret-like evidence.
  • ddg_submit_orderSubmit a paid operator-reviewed DDG order after caller supplies valid payment headers/proof.No findings

    Why it is in this group

    • The name "ddg_submit_order" says "submit": a word for a change.
    Description, as the server wrote it
    Submit a paid operator-reviewed DDG order after caller supplies valid payment headers/proof.
  • ddg_table_extractExtract HTML tables as JSON rows or CSV ($0.003).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
    Extract HTML tables as JSON rows or CSV ($0.003).
  • ddg_token_estimateDeterministic token estimates per model family before a metered call ($0.001).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
    Deterministic token estimates per model family before a metered call ($0.001).
  • ddg_token_metaERC-20 metadata: name, symbol, decimals, total supply ($0.001).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
    ERC-20 metadata: name, symbol, decimals, total supply ($0.001).
  • ddg_tx_smoke_testExercise the one-cent DDG transaction smoke-test route with caller-supplied payment headers.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
    Exercise the one-cent DDG transaction smoke-test route with caller-supplied payment headers.
Only reads 23Show 23 read-only tools
  • ddg_address_validateUS street address parse + normalize with completeness score ($0.003).No findings

    Why it is in this group

    • The name "ddg_address_validate" says "validate": a word for reading.
    Description, as the server wrote it
    US street address parse + normalize with completeness score ($0.003).
  • ddg_agent_distribution_targetsReturn the AI-agent radar surfaces DDG is targeting and their current go-live gates.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
    Return the AI-agent radar surfaces DDG is targeting and their current go-live gates.
  • ddg_agent_reputation_lookupReputation for an agent id / seller endpoint / payTo: DDG-rail settlement history + public signals, explainable score ($0.002).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "ddg_agent_reputation_lookup" says "lookup": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.endpoint), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.endpoint): 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
    Reputation for an agent id / seller endpoint / payTo: DDG-rail settlement history + public signals, explainable score ($0.002).
  • ddg_agent_statusReturn DDG's machine-readable service/rail/MCP status document.Reads private dataNo findings

    Why it is in this group

    • The name "ddg_agent_status" says "status": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "return" and "document": it reads documents.
    Description, as the server wrote it
    Return DDG's machine-readable service/rail/MCP status document.
  • ddg_direct_crypto_addressesReturn DDG's public direct-crypto receiving addresses for manual/beta payment routing.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
    Return DDG's public direct-crypto receiving addresses for manual/beta payment routing.
  • ddg_ethereum_rpc_queryProxy a free read-only Ethereum JSON-RPC query through DDG's private Reth node (sync-gated).No findings

    Why it is in this group

    • The name "ddg_ethereum_rpc_query" says "query": a word for reading.
    Description, as the server wrote it
    Proxy a free read-only Ethereum JSON-RPC query through DDG's private Reth node (sync-gated).
  • ddg_fetch_public_resourceFetch an allowlisted DDG public manifest/doc by id or ddg:// URI with redaction and size caps.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "ddg_fetch_public_resource" says "fetch": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "doc": it reads documents.
    • untrusted-inputThe description's first sentence says "fetch" and "uri": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Fetch an allowlisted DDG public manifest/doc by id or ddg:// URI with redaction and size caps.
  • ddg_list_local_runtime_optionsList free-seat status plus requestable local runtimes such as Ollama, llama.cpp, LM Studio, OpenAI-compatible servers, and vLLM.No findings

    Why it is in this group

    • The name "ddg_list_local_runtime_options" says "list": a word for reading.
    Description, as the server wrote it
    List free-seat status plus requestable local runtimes such as Ollama, llama.cpp, LM Studio, OpenAI-compatible servers, and vLLM.
  • ddg_list_modelsList local/free Ollama models and queryable paid/account-backed route labels.No findings

    Why it is in this group

    • The name "ddg_list_models" says "list": a word for reading.
    Description, as the server wrote it
    List local/free Ollama models and queryable paid/account-backed route labels.
  • ddg_list_servicesList DDG live/manual services from the public pricing and catalog surfaces.No findings

    Why it is in this group

    • The name "ddg_list_services" says "list": a word for reading.
    Description, as the server wrote it
    List DDG live/manual services from the public pricing and catalog surfaces.
  • ddg_mcp_security_profileReturn this MCP wrapper's local security controls and publication gates.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
    Return this MCP wrapper's local security controls and publication gates.
  • ddg_model_compareSame prompt to 2-3 LOCAL models (Ollama) with agreement score ($0.01).No findings

    Why it is in this group

    • The name "ddg_model_compare" says "compare": a word for reading.
    Description, as the server wrote it
    Same prompt to 2-3 LOCAL models (Ollama) with agreement score ($0.01). Account-backed models are rejected.
  • ddg_order_artifactFetch an agent-scoped DDG order artifact when ready.No findings

    Why it is in this group

    • The description's first verb is "fetch": a word for reading.
    Description, as the server wrote it
    Fetch an agent-scoped DDG order artifact when ready.
  • ddg_order_statusPoll an agent-scoped DDG order status URL.Reads text others writeNo findings

    Why it is in this group

    • The name "ddg_order_status" says "status": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Poll an agent-scoped DDG order status URL.
  • ddg_public_resource_indexList allowlisted DDG public manifests/docs available as MCP resources.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "doc": it reads documents.
    Description, as the server wrote it
    List allowlisted DDG public manifests/docs available as MCP resources.
  • ddg_receipt_verify_designDescribe the planned free receipt-verification tool contract.No findings

    Why it is in this group

    • The description's first verb is "describe": a word for reading.
    Description, as the server wrote it
    Describe the planned free receipt-verification tool contract. This is intentionally marked not-live until `/v1/receipt-verify` is implemented and backed by payment-edge audit/state reconciliation.
  • ddg_search_servicesFind DDG agent-callable services matching a natural-language NEED.No findings

    Why it is in this group

    • The name "ddg_search_services" says "search": a word for reading.
    Description, as the server wrote it
    Find DDG agent-callable services matching a natural-language NEED. Returns the best-matching services (service_id, path, price, description) so an agent planner can pick the right one and then invoke it with ddg_call(service, args). This is the entry point to all DDG services — search first, then call.
  • ddg_security_service_catalogReturn DDG's AI-agent cybersecurity service catalog.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
    Return DDG's AI-agent cybersecurity service catalog.
  • ddg_tx_statusTransaction receipt: mined?, success?, block, gas, cost ($0.001).No findings

    Why it is in this group

    • The name "ddg_tx_status" says "status": a word for reading.
    Description, as the server wrote it
    Transaction receipt: mined?, success?, block, gas, cost ($0.001).
  • ddg_wallet_snapshotNative + USDC balance (+optional extra ERC-20s) for an address ($0.002).No findings

    Why it is in this group

    • The name "ddg_wallet_snapshot" says "snapshot": a word for reading.
    Description, as the server wrote it
    Native + USDC balance (+optional extra ERC-20s) for an address ($0.002).
  • ddg_x402_bazaar_readinessReturn CDP x402 Bazaar candidate resources, schema metadata, and settlement indexing gates.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
    Return CDP x402 Bazaar candidate resources, schema metadata, and settlement indexing gates.
  • ddg_x402_supported_chainsReturn all x402/direct-crypto chains DDG supports for AI-agent payment routing.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
    Return all x402/direct-crypto chains DDG supports for AI-agent payment routing.
  • ddg_x402scan_statusReturn DDG's x402scan registration status, resource URLs, and runtime probe guardrails.No findings

    Why it is in this group

    • The name "ddg_x402scan_status" says "status": a word for reading.
    Description, as the server wrote it
    Return DDG's x402scan registration status, resource URLs, and runtime probe guardrails.

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.

36 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 outbound tools breaks every one.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__ddg-agent-services__ddg_agent_reputation_lookup",
      "mcp__ddg-agent-services__ddg_phone_intel",
      "mcp__ddg-agent-services__ddg_seller_trust_badge"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:03 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
31
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 31 tools that change things (1 irreversible, 30 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.daedalusdevelopmentgroup.com/mcp: tools/list returned 54 tools to an anonymous client, including ddg_quote_payment (irreversible), ddg_micro_swarm_preview (write), ddg_call (write), ddg_run_paid_model (write), ddg_submit_order (write) and 26 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

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 0.5.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ddg-agent-services https://mcp.daedalusdevelopmentgroup.com/mcp
claude mcp add --transport http ddg-agent-services https://mcp.daedalusdevelopmentgroup.com/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__ddg-agent-services__ddg_mcp_security_profile",
      "mcp__ddg-agent-services__ddg_public_resource_index",
      "mcp__ddg-agent-services__ddg_fetch_public_resource",
      "mcp__ddg-agent-services__ddg_agent_distribution_targets",
      "mcp__ddg-agent-services__ddg_x402_bazaar_readiness",
      "mcp__ddg-agent-services__ddg_x402scan_status",
      "mcp__ddg-agent-services__ddg_x402_supported_chains",
      "mcp__ddg-agent-services__ddg_direct_crypto_addresses",
      "mcp__ddg-agent-services__ddg_ethereum_rpc_query",
      "mcp__ddg-agent-services__ddg_search_services",
      "mcp__ddg-agent-services__ddg_list_services",
      "mcp__ddg-agent-services__ddg_list_models",
      "mcp__ddg-agent-services__ddg_list_local_runtime_options",
      "mcp__ddg-agent-services__ddg_agent_status",
      "mcp__ddg-agent-services__ddg_order_status",
      "mcp__ddg-agent-services__ddg_order_artifact",
      "mcp__ddg-agent-services__ddg_receipt_verify_design",
      "mcp__ddg-agent-services__ddg_security_service_catalog",
      "mcp__ddg-agent-services__ddg_address_validate",
      "mcp__ddg-agent-services__ddg_model_compare",
      "mcp__ddg-agent-services__ddg_wallet_snapshot",
      "mcp__ddg-agent-services__ddg_tx_status"
    ],
    "ask": [
      "mcp__ddg-agent-services__ddg_micro_swarm_preview",
      "mcp__ddg-agent-services__ddg_call",
      "mcp__ddg-agent-services__ddg_quote_payment",
      "mcp__ddg-agent-services__ddg_run_paid_model",
      "mcp__ddg-agent-services__ddg_submit_order",
      "mcp__ddg-agent-services__ddg_request_ollama_model",
      "mcp__ddg-agent-services__ddg_checkout_conformance",
      "mcp__ddg-agent-services__ddg_skill_safety_scan",
      "mcp__ddg-agent-services__ddg_tx_smoke_test",
      "mcp__ddg-agent-services__ddg_data_query",
      "mcp__ddg-agent-services__ddg_html_to_structured",
      "mcp__ddg-agent-services__ddg_table_extract",
      "mcp__ddg-agent-services__ddg_regex_builder",
      "mcp__ddg-agent-services__ddg_card_fingerprint",
      "mcp__ddg-agent-services__ddg_calendar_parse",
      "mcp__ddg-agent-services__ddg_phone_intel",
      "mcp__ddg-agent-services__ddg_domain_age",
      "mcp__ddg-agent-services__ddg_agent_reputation_lookup",
      "mcp__ddg-agent-services__ddg_seller_trust_badge",
      "mcp__ddg-agent-services__ddg_dispute_evidence_pack",
      "mcp__ddg-agent-services__ddg_receipt_escrow_release",
      "mcp__ddg-agent-services__ddg_robot_fleet_quota_audit",
      "mcp__ddg-agent-services__ddg_robot_geo_fence_audit",
      "mcp__ddg-agent-services__ddg_robot_human_takeover_audit",
      "mcp__ddg-agent-services__ddg_robot_delegation_chain_audit",
      "mcp__ddg-agent-services__ddg_token_estimate",
      "mcp__ddg-agent-services__ddg_prompt_cost_budget",
      "mcp__ddg-agent-services__ddg_eth_gas",
      "mcp__ddg-agent-services__ddg_token_meta",
      "mcp__ddg-agent-services__ddg_crypto_price",
      "mcp__ddg-agent-services__ddg_gas_multi",
      "mcp__ddg-agent-services__ddg_crypto_portfolio"
    ],
    "deny": []
  }
}

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 ddg-agent-services. Review it before you use it.

Capability tags behind 8 rules
  • mcp__ddg-agent-services__ddg_public_resource_index private-data
  • mcp__ddg-agent-services__ddg_fetch_public_resource private-data, untrusted-input
  • mcp__ddg-agent-services__ddg_agent_status private-data
  • mcp__ddg-agent-services__ddg_order_status untrusted-input
  • mcp__ddg-agent-services__ddg_data_query untrusted-input
  • mcp__ddg-agent-services__ddg_phone_intel outbound
  • mcp__ddg-agent-services__ddg_agent_reputation_lookup untrusted-input, outbound
  • mcp__ddg-agent-services__ddg_seller_trust_badge outbound

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.daedalusdevelopmentgroup/ddg-agent-services-mcp/verify?hash=2e867e91e0747637b9cee51f9efbc00db5d45b1f9e824e1453b16aa856e7d582" | jq -e '.changed == false'

Pinned hash 2e867e91e074, from Nov 16, 2026, 15:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp.svg)](https://radar.anlyon.com/servers/io.github.daedalusdevelopmentgroup/ddg-agent-services-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:29 UTC.

DDG Agent Services MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the DDG Agent Services MCP server safe?

No scan can promise that. What its definitions show: 54 tools, 31 of which can change, send or delete something, and 0 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 DDG Agent Services MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the DDG Agent Services MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: ddg_quote_payment.

What tools does the DDG Agent Services MCP server have?

54 tools: 1 irreversible, 30 write, 23 read. ddg_quote_payment, ddg_micro_swarm_preview, ddg_call, ddg_run_paid_model, ddg_submit_order, ddg_request_ollama_model, ddg_checkout_conformance, ddg_skill_safety_scan and 46 more.

Does the DDG Agent Services MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the DDG Agent Services MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): ddg_phone_intel, ddg_agent_reputation_lookup and ddg_seller_trust_badge.

Has the DDG Agent Services MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.