flarewatch MCP server
io.flarewatch/flarewatchflarewatch.iostreamable-httpv0.1.5Scanned
Verifiable Flare & Songbird data: validator scores, FTSO accuracy, prices, wallet intelligence.
26 tools: 2 change things and 24 only read.
- Reads private data · 0
- Reads text others write · 26
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. 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 flarewatch MCP server can do
The flarewatch MCP server is published by flarewatch.io, a domain the MCP Registry verified. It has 26 tools. It can create or change data (2 tools: simulate_delegation_rewards and verify_response), but cannot delete data. 24 tools only read.
26 tools bring in text other people can write (get_flare_validators, get_validator_score, get_ftso_providers and 23 more).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 0.1.5.
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.
26 tools
Changes things 2Claude Code: ask
simulate_delegation_rewardsEstimate annual WFLR FTSO-delegation rewards for delegating an amount to a Flare FTSO provider (defaults to FlareWatch).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 Estimate annual WFLR FTSO-delegation rewards for delegating an amount to a Flare FTSO provider (defaults to FlareWatch). Annualizes the provider's latest realized per-epoch reward rate (rate x ~104.29 epochs/yr). Returns estimated APR and annual/monthly reward in FLR. A projection, not a guarantee; FTSO delegation only, not P-chain staking. found=false when the provider isn't cached.
Annotations the server declares
- title: Simulate Delegation Rewards
- readOnlyHint: true
- openWorldHint: true
verify_responseVerify that a previously-served FlareWatch MCP response really came from this server.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 Verify that a previously-served FlareWatch MCP response really came from this server. Pass the structured envelope WITHOUT the verification_signature field as payload, and the signature you received as signature. Returns valid=true when the HMAC matches. Useful for cross-AI citation verification.
Annotations the server declares
- title: Verify Response
- readOnlyHint: true
- openWorldHint: true
Only reads 24Show 24 read-only tools
compare_ftso_providersSide-by-side comparison of up to 10 FTSO providers on Flare or Songbird.Reads text others writeNo findings
Why it is in this group
- The name "compare_ftso_providers" says "compare": 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 Side-by-side comparison of up to 10 FTSO providers on Flare or Songbird. Rows returned in the order supplied (no re-ranking by FlareWatch). Flare rows include the composite Score; Songbird rows expose vote power, fee, last-epoch reward rate. Missing addresses return found=false with null fields.
Annotations the server declares
- title: Compare FTSO Providers
- readOnlyHint: true
- openWorldHint: true
compare_validatorsSide-by-side comparison of up to 10 Flare validators by NodeID.Reads text others writeNo findings
Why it is in this group
- The name "compare_validators" says "compare": 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 Side-by-side comparison of up to 10 Flare validators by NodeID. Rows returned in the order supplied (no re-ranking by FlareWatch). Each row carries score, stake, fee, uptime, capacity, APR, and stake-period expiry. Missing NodeIDs return found=false with null fields.
Annotations the server declares
- title: Compare Validators
- readOnlyHint: true
- openWorldHint: true
get_agent_capabilitiesReturn the FlareWatch agent's capability surface: autonomous-vs-total playbook counts per family (validator families are propose-only — autonomous 0 by design), autonomous fraction…Reads text others writeNo findings
Why it is in this group
- The name "get_agent_capabilities" says "get": 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 Return the FlareWatch agent's capability surface: autonomous-vs-total playbook counts per family (validator families are propose-only — autonomous 0 by design), autonomous fraction across agent-owned surfaces, drill correctness, defects caught, and recovery counts (deterministic = the node's own controllers; agentic = the agent). Source: hourly signed snapshot; available=false when unavailable.
Annotations the server declares
- title: Get Agent Capabilities
- readOnlyHint: true
- openWorldHint: true
get_agent_statusReturn the FlareWatch agent's reliability scorecard from its hourly signed snapshot: autonomous fraction across agent-owned surfaces (validator families are propose-only) + per-fam…Reads text others writeNo findings
Why it is in this group
- The name "get_agent_status" says "get": 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 Return the FlareWatch agent's reliability scorecard from its hourly signed snapshot: autonomous fraction across agent-owned surfaces (validator families are propose-only) + per-family breakdown, recovery counts (deterministic = the node's own controllers; agentic = the agent; 30-day window), drill correctness, defects caught, and human-in-the-loop queue depth. available=false when unavailable.
Annotations the server declares
- title: Get Agent Status
- readOnlyHint: true
- openWorldHint: true
get_chain_activityReturn live Flare C-chain activity: transactions per second, average block time, block utilization, gas price (gwei), average fee per tx, latest block number, and all-time totals (…Reads text others writeNo findings
Why it is in this group
- The name "get_chain_activity" says "get": 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 Return live Flare C-chain activity: transactions per second, average block time, block utilization, gas price (gwei), average fee per tx, latest block number, and all-time totals (transactions, addresses, blocks). Source is a live block sample plus explorer stats. Nulls returned when a leg is unavailable.
Annotations the server declares
- title: Get Chain Activity
- readOnlyHint: true
- openWorldHint: true
get_defi_tvlReturn total value locked (USD) across the Flare DeFi ecosystem with a per-protocol breakdown (protocol name, TVL, token count).Reads text others writeNo findings
Why it is in this group
- The name "get_defi_tvl" says "get": 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 Return total value locked (USD) across the Flare DeFi ecosystem with a per-protocol breakdown (protocol name, TVL, token count). Source is on-chain reads valued at current prices. available=false / total null when the price-dependent TVL read is unavailable.
Annotations the server declares
- title: Get DeFi TVL
- readOnlyHint: true
- openWorldHint: true
get_fassets_statusReturn FAssets status on Flare: for each FAsset (e.g.Reads text others writeNo findings
Why it is in this group
- The name "get_fassets_status" says "get": 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 Return FAssets status on Flare: for each FAsset (e.g. FXRP), its symbol, underlying asset, minted amount, and USD TVL (minted x underlying price), plus aggregate total_tvl_usd. Source is on-chain totalSupply reads valued at current prices. available=false when the read fails or none are minted.
Annotations the server declares
- title: Get FAssets Status
- readOnlyHint: true
- openWorldHint: true
get_flare_pricesLatest FLR, SGB and XRP prices in USD and major fiats (EUR, GBP, AUD, JPY, CAD).Reads text others writeNo findings
Why it is in this group
- The name "get_flare_prices" says "get": 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 Latest FLR, SGB and XRP prices in USD and major fiats (EUR, GBP, AUD, JPY, CAD). Each asset has its OWN source (ftso oracle, or coingecko fallback) and sources can differ within one response, so check source per asset. degraded=true only when a whole upstream fails: one asset falling back does NOT set it, nor a missing rate (fx.<cur>=null). fx is the shared USD-to-fiat rate: fiat = usd * fx.
Annotations the server declares
- title: Get Flare Prices
- readOnlyHint: true
- openWorldHint: true
get_flare_validatorsList Flare P-Chain validators with FlareWatch composite Score, stake, fee, uptime, and capacity.Reads text others writeNo findings
Why it is in this group
- The name "get_flare_validators" says "get": 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 List Flare P-Chain validators with FlareWatch composite Score, stake, fee, uptime, and capacity. Sort by score (default), stake, or apy. Pure on-chain + computed data; no editorial ranking. limit caps at 100.
Annotations the server declares
- title: Get Flare Validators
- readOnlyHint: true
- openWorldHint: true
get_flarewatch_sgb_entityReturn FlareWatch's Songbird FTSO entity's live on-chain stats: WSGB vote power, self-balance, current delegation fee, and per-WSGB reward rate from the last finished reward epoch.Reads text others writeNo findings
Why it is in this group
- The name "get_flarewatch_sgb_entity" says "get": 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 Return FlareWatch's Songbird FTSO entity's live on-chain stats: WSGB vote power, self-balance, current delegation fee, and per-WSGB reward rate from the last finished reward epoch. Source is direct on-chain reads (WNat + WNatDelegationFee + RewardManager). configured=false indicates the entity address isn't set yet.
Annotations the server declares
- title: Get FlareWatch SGB Entity
- readOnlyHint: true
- openWorldHint: true
get_flarewatch_validatorReturn FlareWatch's own Flare P-Chain validators — same scoring algorithm as every other validator, no promotional weighting.Reads text others writeNo findings
Why it is in this group
- The name "get_flarewatch_validator" says "get": 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 Return FlareWatch's own Flare P-Chain validators — same scoring algorithm as every other validator, no promotional weighting. One row per node (label, self-bond, delegations, stake count, fee, uptime, expiry, Score) plus entity totals. is_live=false marks a cold-load fallback row whose live figures are not measurements.
Annotations the server declares
- title: Get FlareWatch Validator
- readOnlyHint: true
- openWorldHint: true
get_ftso_provider_historyReturn one Flare FTSO provider's per-epoch reward-rate and Score trend over the last tracked reward epochs (up to 30, newest first).Reads text others writeNo findings
Why it is in this group
- The name "get_ftso_provider_history" says "get": 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 Return one Flare FTSO provider's per-epoch reward-rate and Score trend over the last tracked reward epochs (up to 30, newest first). address may be the provider's entity address or its delegation address. found=false when the provider isn't in the tracked window.
Annotations the server declares
- title: Get FTSO Provider History
- readOnlyHint: true
- openWorldHint: true
get_ftso_provider_metricsReturn detailed metrics for one FTSO data provider on Flare or Songbird: fee, reward rate, uptime, vote power, delegator count, and (Flare) the FlareWatch composite Score plus the …Reads text others writeNo findings
Why it is in this group
- The name "get_ftso_provider_metrics" says "get": 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 Return detailed metrics for one FTSO data provider on Flare or Songbird: fee, reward rate, uptime, vote power, delegator count, and (Flare) the FlareWatch composite Score plus the provider's rank and percentile by score and by reward rate among all providers (provider_count is the denominator). address must be a lowercase 0x EVM address.
Annotations the server declares
- title: Get FTSO Provider Metrics
- readOnlyHint: true
- openWorldHint: true
get_ftso_providersList FTSO data providers on Flare or Songbird.Reads text others writeNo findings
Why it is in this group
- The name "get_ftso_providers" says "get": 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 List FTSO data providers on Flare or Songbird. Flare rows include FlareWatch composite Score; Songbird rows expose vote power, fee, and last-epoch reward rate (no score on SGB by design). Default sort: score (FLR) / vote power (SGB). limit caps at 100.
Annotations the server declares
- title: Get FTSO Providers
- readOnlyHint: true
- openWorldHint: true
get_my_claimableReturn what the calling wallet can claim right now: Flare FTSO delegation, P-chain staking (mirror), provider fee and validation rewards in FLR, the unclaimed epoch range, and Song…Reads text others writeNo findings
Why it is in this group
- The name "get_my_claimable" says "get": 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 Return what the calling wallet can claim right now: Flare FTSO delegation, P-chain staking (mirror), provider fee and validation rewards in FLR, the unclaimed epoch range, and Songbird FTSO rewards. Types owed but not yet priced on-chain are listed in flr_pending_resolution. Requires OAuth scope wallet:read.
Annotations the server declares
- title: Get My Claimable
- readOnlyHint: true
- openWorldHint: true
get_my_delegationsReturn the calling wallet's WFLR FTSO delegations and P-chain validator delegations.Reads text others writeNo findings
Why it is in this group
- The name "get_my_delegations" says "get": 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 Return the calling wallet's WFLR FTSO delegations and P-chain validator delegations. Requires OAuth scope wallet:read. The wallet is resolved from the OAuth token; no input arg accepts a wallet address (cross-tenancy isolation).
Annotations the server declares
- title: Get My Delegations
- readOnlyHint: true
- openWorldHint: true
get_my_portfolio_summaryReturn the calling wallet's FLR and SGB balances and their USD valuations.Reads text others writeNo findings
Why it is in this group
- The name "get_my_portfolio_summary" says "get": 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 Return the calling wallet's FLR and SGB balances and their USD valuations. Native and wrapped (WFLR / WSGB) balances are reported separately; wrapped balances roll into the per-token USD values and the total. Requires OAuth scope wallet:read.
Annotations the server declares
- title: Get My Portfolio Summary
- readOnlyHint: true
- openWorldHint: true
get_my_rewards_historyReturn the calling wallet's reward history: FLR claimed per recent reward epoch (at least the last 30 days), split into FTSO delegation, P-chain staking and provider fee (including…Reads text others writeNo findings
Why it is in this group
- The name "get_my_rewards_history" says "get": 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 Return the calling wallet's reward history: FLR claimed per recent reward epoch (at least the last 30 days), split into FTSO delegation, P-chain staking and provider fee (including auto-claims), plus cumulative validation rewards and burn-window countdowns. Read-only. Requires OAuth scope wallet:read.
Annotations the server declares
- title: Get My Rewards History
- readOnlyHint: true
- openWorldHint: true
get_network_economicsReturn Flare's monetary metrics: circulating and committed supply, total staked, staking ratio, WFLR supply, annualized inflation (rate + FLR/yr), and the FLR burn rate (daily + an…Reads text others writeNo findings
Why it is in this group
- The name "get_network_economics" says "get": 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 Return Flare's monetary metrics: circulating and committed supply, total staked, staking ratio, WFLR supply, annualized inflation (rate + FLR/yr), and the FLR burn rate (daily + annualized estimate) with net supply change. Source is on-chain reads plus a live block sample for the burn estimate. Nulls (not zeros) returned for any leg whose on-chain read fails.
Annotations the server declares
- title: Get Network Economics
- readOnlyHint: true
- openWorldHint: true
get_network_statusReturn current FTSO reward-epoch state for Flare (default) or Songbird: current epoch ID, when it started, how far into the epoch we are, and how many seconds remain.Reads text others writeNo findings
Why it is in this group
- The name "get_network_status" says "get": 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 Return current FTSO reward-epoch state for Flare (default) or Songbird: current epoch ID, when it started, how far into the epoch we are, and how many seconds remain. Source is FlareSystemsManager on-chain reads. Nulls returned when on-chain read fails.
Annotations the server declares
- title: Get Network Status
- readOnlyHint: true
- openWorldHint: true
get_payment_optionsReturn machine-readable payment options for paid FlareWatch capacity: deposit USDT0 on Flare and the sending wallet is credited compute units (CU) that never expire.Reads text others writeNo findings
Why it is in this group
- The name "get_payment_options" says "get": 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 Return machine-readable payment options for paid FlareWatch capacity: deposit USDT0 on Flare and the sending wallet is credited compute units (CU) that never expire. Includes the deposit address, credit rate, and balance URL. provisioned=false means the rail is not accepting deposits yet.
Annotations the server declares
- title: Get Payment Options
- readOnlyHint: true
- openWorldHint: true
get_recent_agent_actionsReturn the FlareWatch agent's recent action feed: surface, action kind (observation/propose/topup/rollback/claim/etc), outcome, and detect-to-remediate latency on the agent's own r…Reads text others writeNo findings
Why it is in this group
- The name "get_recent_agent_actions" says "get": 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 Return the FlareWatch agent's recent action feed: surface, action kind (observation/propose/topup/rollback/claim/etc), outcome, and detect-to-remediate latency on the agent's own recoveries. Validator-surface entries are proposals only — the node's own controllers act, never the agent. Source: hourly signed snapshot, verifiable via chain_verify_url; available=false when it is unavailable.
Annotations the server declares
- title: Get Recent Agent Actions
- readOnlyHint: true
- openWorldHint: true
get_validator_scoreReturn the FlareWatch composite Score and full per-dimension breakdown for one Flare validator by NodeID.Reads text others writeNo findings
Why it is in this group
- The name "get_validator_score" says "get": 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 Return the FlareWatch composite Score and full per-dimension breakdown for one Flare validator by NodeID. Each dimension carries its raw score, max, and the detail string explaining the score (e.g. 'Active outage · 3 consecutive missed epochs'). Methodology link returned.
Annotations the server declares
- title: Get Validator Score
- readOnlyHint: true
- openWorldHint: true
list_ftso_feedsList the FTSO block-latency price feeds Flare's oracle provides (e.g.Reads text others writeNo findings
Why it is in this group
- The name "list_ftso_feeds" says "list": 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 List the FTSO block-latency price feeds Flare's oracle provides (e.g. FLR/USD, BTC/USD, ETH/USD) with Flare's published risk tier for each (low/medium/high/new — volatility + liquidity). Optionally filter by risk. These are the symbols the on-chain oracle prices; this tool returns the feed list, not live prices.
Annotations the server declares
- title: List FTSO Feeds
- readOnlyHint: true
- 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write26
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.flarewatch.io/.well-known/oauth-protected-resource
- Authorization servers
- https://mcp.flarewatch.io
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.flarewatch.io/api/mcp: tools/list returned 26 tools to an anonymous client, including simulate_delegation_rewards (write), verify_response (write)
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.
Tools1 changed.~1 changedView diff
- Changed:get_flarewatch_validatorOnly readsdescription
Install
Pinned to version 0.1.5. Values in angle brackets are yours to fill in.
claude mcp add --transport http flarewatch https://mcp.flarewatch.io/api/mcpclaude mcp add --transport http flarewatch https://mcp.flarewatch.io/api/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__flarewatch__get_flare_validators",
"mcp__flarewatch__get_validator_score",
"mcp__flarewatch__get_ftso_providers",
"mcp__flarewatch__get_ftso_provider_metrics",
"mcp__flarewatch__get_network_status",
"mcp__flarewatch__get_flarewatch_validator",
"mcp__flarewatch__get_flarewatch_sgb_entity",
"mcp__flarewatch__get_flare_prices",
"mcp__flarewatch__get_recent_agent_actions",
"mcp__flarewatch__get_agent_capabilities",
"mcp__flarewatch__get_agent_status",
"mcp__flarewatch__get_network_economics",
"mcp__flarewatch__get_fassets_status",
"mcp__flarewatch__get_defi_tvl",
"mcp__flarewatch__get_chain_activity",
"mcp__flarewatch__get_ftso_provider_history",
"mcp__flarewatch__list_ftso_feeds",
"mcp__flarewatch__get_payment_options",
"mcp__flarewatch__compare_validators",
"mcp__flarewatch__compare_ftso_providers",
"mcp__flarewatch__get_my_delegations",
"mcp__flarewatch__get_my_claimable",
"mcp__flarewatch__get_my_portfolio_summary",
"mcp__flarewatch__get_my_rewards_history"
],
"ask": [
"mcp__flarewatch__simulate_delegation_rewards",
"mcp__flarewatch__verify_response"
],
"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 flarewatch. Review it before you use it.
Capability tags behind 26 rules
- mcp__flarewatch__get_flare_validators untrusted-input
- mcp__flarewatch__get_validator_score untrusted-input
- mcp__flarewatch__get_ftso_providers untrusted-input
- mcp__flarewatch__get_ftso_provider_metrics untrusted-input
- mcp__flarewatch__get_network_status untrusted-input
- mcp__flarewatch__get_flarewatch_validator untrusted-input
- mcp__flarewatch__get_flarewatch_sgb_entity untrusted-input
- mcp__flarewatch__get_flare_prices untrusted-input
- mcp__flarewatch__get_recent_agent_actions untrusted-input
- mcp__flarewatch__get_agent_capabilities untrusted-input
- mcp__flarewatch__get_agent_status untrusted-input
- mcp__flarewatch__get_network_economics untrusted-input
- mcp__flarewatch__get_fassets_status untrusted-input
- mcp__flarewatch__get_defi_tvl untrusted-input
- mcp__flarewatch__get_chain_activity untrusted-input
- mcp__flarewatch__get_ftso_provider_history untrusted-input
- mcp__flarewatch__list_ftso_feeds untrusted-input
- mcp__flarewatch__get_payment_options untrusted-input
- mcp__flarewatch__simulate_delegation_rewards untrusted-input
- mcp__flarewatch__compare_validators untrusted-input
- mcp__flarewatch__compare_ftso_providers untrusted-input
- mcp__flarewatch__verify_response untrusted-input
- mcp__flarewatch__get_my_delegations untrusted-input
- mcp__flarewatch__get_my_claimable untrusted-input
- mcp__flarewatch__get_my_portfolio_summary untrusted-input
- mcp__flarewatch__get_my_rewards_history 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.flarewatch/flarewatch/verify?hash=129b7ee9dc1152f505619072324635138f0dad1862a8ab741c2da638772098ab" | jq -e '.changed == false'Pinned hash 129b7ee9dc11, from Nov 11, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.flarewatch/flarewatch/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.flarewatch/flarewatch)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:13 UTC.
flarewatch MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the flarewatch MCP server safe?
- No scan can promise that. What its definitions show: 26 tools, 2 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 flarewatch MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the flarewatch MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the flarewatch MCP server have?
- 26 tools: 2 write, 24 read. simulate_delegation_rewards, verify_response, get_flare_validators, get_validator_score, get_ftso_providers, get_ftso_provider_metrics, get_network_status, get_flarewatch_validator and 18 more.
Does the flarewatch MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the flarewatch MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the flarewatch MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.