FET112 Watchdog MCP server
Which MCP servers are FET112 Watchdog's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-28
- Registry namecom.fet112/fet112verified in the MCP registry
The registry name sits under fet112.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools14
- Server calls itselffet112-watchdog
- Server version1.6.3-pre-action-rc1
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 635 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 6 of the 7 days it takes to judge reliability.
Once connected
- For "query signed security reports through an agent interface", the likely first call is fet112.security_report.
- Parameters are untyped or undescribed in 10 of 14 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer797 ms
- Space in an agent's context≈ 2,246 tokensthe definitions of all its tools (14), which an agent carries on every turn
- Tool definitionsB · 88 of 100
- Typed results0 of 14 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 10 of 14
What an agent can do with it
- not sure · review conversion and minting activity for security anomalies
- not sure · track privileged role grants and revocations
- can do · query signed security reports through an agent interface
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
fet112.network_state_attestationAttest observed native fetchhub-4 gas, transactions and blocks for the latest available finalized hour (four 15-minute windows). Signed coverage, source cursor, issue/expiry times and explicit fresh/stale/partial/unavailable observation…
fet112.verify_network_state_attestationVerify canonical signed payload, pinned identity, expiry and source age independently. No live chain canonicality check.
fet112.network_state_keysDiscover current Ed25519 public key and fingerprint. Discovery is not an independent trust anchor.
fet112.analytics_catalogDiscover supported native metrics, exact semantics, aggregations, coverage requirements and executable query examples. No model or chain RPC calls.
fet112.analytics_queryExecute a validated read-only native Fetch query: sums, extrema, weighted means, groupings, rollups and comparable UTC windows. Read analytics_catalog first. Missing coverage is an error, never zero. Top rankings cannot be combined across…
fet112.transaction_comparisonCompare native fetchhub-4 transactions TODAY and YESTERDAY over exactly the same elapsed UTC interval, ending at today's latest authoritative finalized cutoff. Both windows come from one SQLite snapshot. Returns counts, success rates…
fet112.verify_quantitative_contextVerify the separate native quantitative Ed25519 attestation and full consumer policy. Supply a trusted fingerprint to verify identity; does not evaluate chain canonicality, freshness or security.
fet112.transaction_activityNative fetchhub-4 transactions included in blocks for today or yesterday UTC. Returns successful/failed/total counts, success percentage and average TPS over contiguous finalized 15-minute buckets. Empty periods with valid coverage have…
fet112.staking_contextObserved native Fetch staking FLOW on fetchhub-4 for today or yesterday UTC, using finalized 15-minute buckets and comparable historical periods. Returns exact afet strings, coverage and source cursor. This is NOT total staked balance, a…
fet112.network_statusReturn FET112's current machine-facing network status. The verdict is copied from SecurityReportV1 for configured Fetch/ASI contracts on Ethereum (chain_id=1). Do not apply it to native fetchhub-4 traffic.
fet112.recent_incidentsReturn bounded recent incidents associated with the current signed report context.
fet112.security_reportReturn the current signed SecurityReportV1 for configured Fetch/ASI contracts on Ethereum (chain_id=1). It does not evaluate native fetchhub-4 traffic.
fet112.pre_action_checkDeterministic pre-flight over the current watched Ethereum security environment. V1 commits the intended action but does not classify destination, amount, asset, business authorization or simulate the transaction.
fet112.verify_attestationVerify an arbitrary SecurityReportV1/attestation pair offline, optionally against a trusted FET112 key fingerprint.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"fet112": {
"type": "http",
"url": "https://www.fet112.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http fet112 https://www.fet112.com/mcpclaude.ai, ChatGPT and other clients: add https://www.fet112.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.