# MCP Verification Gate: check an MCP server or an A2A agent before you connect or delegate > Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key. - name: io.github.ogasurfproject-jpg/hs-verify-gate - version: 0.4.20 - connection class: R0 (autonomous) - trust: 92/100 flags: duplicate-repo - quality: 86/100 (good) - owner: not claimed - descriptor: https://api.protogrid.dev/v1/servers/io.github.ogasurfproject-jpg%2Fhs-verify-gate - tools: https://api.protogrid.dev/v1/servers/io.github.ogasurfproject-jpg%2Fhs-verify-gate/tools **An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe. ## Connection (mcpServers) ```json { "mcpServers": { "hs-verify-gate": { "type": "http", "url": "https://gate.horizonshield.dev/mcp" } } } ``` ## Trust - hygiene: 80 - liveness: 98 - freshness: 100 - provenance: 90 - drivers: +repository +namespace-matches-repo +website +reachable +uptime-96% +updated-22d-ago -duplicate-repo(9 names) - Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. ## Quality 86/100 (good) ### protocol: 75 (weight 25) - warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28 - n/a `protocol.stateless`: only applies to 2026-07-28 servers - pass `protocol.transport`: streamable HTTP - n/a `protocol.list_ttl`: only applies to 2026-07-28 servers ### authorization: n/a (weight 15) - n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth - n/a `auth.secret_in_url`: no templated URL ### tool hygiene: 100 (weight 30) - pass `tools.descriptions`: every tool has a description - pass `tools.description_length`: descriptions are concise - pass `tools.schemas`: every tool has an object input schema - pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint - pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint - pass `tools.token_cost`: about 1,319 tokens to load every tool - pass `tools.api_dump`: tools are not a one-to-one API dump ### stability: 75 (weight 15) - warn `stability.changes`: 8 tool changes in 30 days - pass `stability.rug_pull`: no tool changed its meaning under the same name ### dependencies: n/a (weight 15) - n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package - tools: 6, about 1,319 tokens to load them all - tool set hash: 4ce987f21161dc07002fb9dae997ab8f - tools last changed: 2026-10-08T13:09:52.257Z - badge: [![protogrid quality](https://protogrid.dev/badge/io.github.ogasurfproject-jpg/hs-verify-gate.svg)](https://protogrid.dev/servers/io.github.ogasurfproject-jpg/hs-verify-gate) - Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. ### Tool changes - 2026-10-08 `check_conformance` changed (description, inputSchema, outputSchema) - before: Measure a public MCP endpoint against five conditions: it speaks MCP, it publishes an A2A agent card, it declares who pays it, identical input returns identical output, and the verdict itself can be recomputed by anyone. Free, no key. Conformance and disclosure only; this says nothing about whether any figure the checked server returns is correct. By default no tool on the checked server is called, so determinism comes back as not measured rather than guessed. Set allow_tool_call true only for a server you control. - after: Measure a public MCP endpoint against five conditions: it speaks MCP, it publishes an A2A agent card, it declares who pays it, identical input returns identical output, and the verdict itself can be recomputed by anyone. Free, no key. Conformance and disclosure only; this says nothing about whether any figure the checked server returns is correct. By default no tool on the checked server is called, so determinism comes back as not measured rather than guessed. It is measured when the owner has published /.well-known/mcp-conduct.json with allow_tool_call true. - 2026-10-07 `preflight_agent` changed (outputSchema) - 2026-10-07 `is_verified` changed (outputSchema) - 2026-10-07 `lookup_server` changed (description, outputSchema) - before: Look up what this register already holds about an MCP endpoint: whether it is watched, how often it is re-measured, how many measurements exist, when the first and latest were taken, and the latest verdict with the record_sha256 you can recompute yourself. Reads stored measurements only. It contacts nothing and measures nothing, so use check_conformance for a fresh reading. An endpoint that is absent is reported as absent and that is NOT a negative verdict: it means nobody has measured it here, not that it failed. - after: Returns one record (not a list). Look up what this register already holds about an MCP endpoint: whether it is watched, how often it is re-measured, how many measurements exist, when the first and latest were taken, and the latest verdict with the record_sha256 you can recompute yourself. Reads stored measurements only. It contacts nothing and measures nothing, so use check_conformance for a fresh reading. An endpoint that is absent is reported as absent and that is NOT a negative verdict: it means nobody has measured it here, not that it failed. - 2026-10-07 `verify_verdict` changed (outputSchema) - 2026-10-07 `check_conformance` changed (outputSchema) - 2026-10-07 `get_conditions` changed (outputSchema) - 2026-09-28 `preflight_agent` added - Call this before handing work to an A2A agent you have not used before. Fetches the agent's public card (https:///.well-known/agent-card.json, one request), reports whether it declares the A2A Conduct Extension, who it says pays it (the compensation declaration, as declared and not verified), whether the card carries a signature, the endpoints it asks to be measured on, and this register's stored reading for each (verified is true only when the latest scheduled measurement passed; null otherwise, never false), plus where to file your own witness walk. Measures nothing new and returns counts and pointers, never a score. An agent that does not declare the extension is reported as such, which is not a negative verdict. Full history: https://api.protogrid.dev/v1/servers/io.github.ogasurfproject-jpg%2Fhs-verify-gate/changes ## Remotes - https://gate.horizonshield.dev/mcp (streamable-http, auth none, reachable true, uptime30d 0.95689654) ## Packages _none_ ## Tools (6) - `check_conformance`: Measure a public MCP endpoint against five conditions: it speaks MCP, it publishes an A2A agent card, it declares who pays it, identical input returns identical output, and the verdict itself can be recomputed by anyone. Free, no key. Conformance and disclosure only; this says nothing about whether any figure the checked server returns is correct. By default no tool on the checked server is called, so determinism comes back as not measured rather than guessed. It is measured when the owner has published /.well-known/mcp-conduct.json with allow_tool_call true. - `get_conditions`: Return the five conditions this gate measures, what it explicitly does not verify, and the tier definitions. Takes no arguments and returns identical output every time. Read this before running a check so you know what a verdict does and does not claim. - `is_verified`: A single machine-first answer for an agent deciding whether to trust an MCP endpoint BEFORE it connects. Returns verified (true only when the latest scheduled measurement passed every measured condition; null otherwise, never false), a state enum saying which case it is, measured_at, and a record_sha256 with a recompute_url so you can check the verdict without trusting this gate. Reads the stored register only: it contacts nothing and measures nothing. Absent and pending are reported honestly and are NOT negative verdicts. For a fresh measurement rather than the stored one, use check_conformance. - `lookup_server`: Returns one record (not a list). Look up what this register already holds about an MCP endpoint: whether it is watched, how often it is re-measured, how many measurements exist, when the first and latest were taken, and the latest verdict with the record_sha256 you can recompute yourself. Reads stored measurements only. It contacts nothing and measures nothing, so use check_conformance for a fresh reading. An endpoint that is absent is reported as absent and that is NOT a negative verdict: it means nobody has measured it here, not that it failed. - `preflight_agent`: Call this before handing work to an A2A agent you have not used before. Fetches the agent's public card (https:///.well-known/agent-card.json, one request), reports whether it declares the A2A Conduct Extension, who it says pays it (the compensation declaration, as declared and not verified), whether the card carries a signature, the endpoints it asks to be measured on, and this register's stored reading for each (verified is true only when the latest scheduled measurement passed; null otherwise, never false), plus where to file your own witness walk. Measures nothing new and returns counts and pointers, never a score. An agent that does not declare the extension is reported as such, which is not a negative verdict. - `verify_verdict`: Take a verdict this gate issued and recompute its record_sha256 independently. Removes record_sha256 and recompute_note, serialises the remainder in key order, and hashes it. Returns whether the verdict was altered after it was issued. You do not have to trust the party that issued the verdict, including this one.