MCP Verification Gate: check an MCP server or an A2A agent before you connect or delegate
Server Details
Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- ogasurfproject-jpg/horizon-shield
- GitHub Stars
- 2
- Server Listing
- HORIZON SHIELD KIRA
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Most tools target clearly distinct actions: get_conditions is static documentation, check_conformance performs a fresh measurement, preflight_agent handles A2A agents rather than MCP servers, and verify_verdict recomputes a hash. The one soft overlap is is_verified vs lookup_server, which both read the stored register without contacting anything; descriptions do differentiate them (single boolean answer vs full record), but an agent can easily pick the wrong one for a 'tell me about this server' question.
All names are snake_case with a leading verb, giving a predictable shape across the set. The only deviation is is_verified, an adjective predicate rather than a verb_noun action, and the semantics of check_ vs verify_ are subtly similar (check_conformance vs verify_verdict), which weakens the pattern slightly without breaking readability.
Six tools is well-scoped for a verification gate: one per lifecycle step (learn the criteria, measure fresh, read stored boolean, read stored record, preflight an agent, recompute a verdict). Each earns its place and nothing looks like padding or a duplicate endpoint.
The surface covers the core loop of 'understand the claim, measure, read stored verdict, verify the verdict independently' for both MCP servers and A2A agents. Gaps exist around discovery and lifecycle: there is no way to enumerate or list watched endpoints, no tool to register/request re-measurement, no per-measurement history, and the 'file your own witness walk' action is only returned as a pointer rather than a tool.
Publisher details
- Operator
- The HORIZONs Co., Ltd. · Publisher source
- Operator website
- https://shield.the-horizons-innovation.com
- Vendor relationship
- Independent · Publisher source
- Documentation
- https://gate.horizonshield.dev/spec
- Privacy policy
- Not provided
- Trust center
- https://gate.horizonshield.dev/self
- Restrictions
- None. Free, read only, no key. · Publisher source
Available Tools
6 toolscheck_conformanceCheck an MCP server for conformance and disclosureARead-onlyInspect
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.
Inputs: endpoint (required), allow_tool_call. Returns: gate, checks, status, endpoint, +21 more
get_conditionsGet the conformance conditionsARead-onlyIdempotentInspect
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.
Inputs: no named parameters. Returns: Deterministic. Takes no arguments, looks nothing up, and returns the same docum…
is_verifiedOne glance: is this MCP server verified, with proofARead-onlyIdempotentInspect
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.
Inputs: endpoint (required). Returns: A one-glance answer for an agent deciding whether to trust an MCP endpoint BEFO…
lookup_serverLook up an MCP server on this registerARead-onlyIdempotentInspect
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.
Inputs: endpoint (required). Returns: Returns one record (not a list): what this register holds for the single endpoi…
preflight_agentBefore delegating: check an A2A agent's card, who pays it, and its register readingARead-onlyIdempotentInspect
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.
Inputs: agent (required). Returns: What the agent's public card declares and what this register holds for the endp…
verify_verdictRecompute a verdict hash without trusting the issuerARead-onlyIdempotentInspect
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.
Inputs: record (required). Returns: note, method, reason, verified, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Scans an MCP server for security gaps before your agent connects. Free tier, no signup.
Free, read-only security scanner for remote MCP servers, before you connect them.
See which AI models fall for traps in everyday jobs, and check or scan any MCP server, skill or package before your agent installs it. No sign-in; read-only; returns structured data.
Free agent-service discovery, OpenAPI document checks, and receipt verification. No API key needed.
Related MCP Servers
- AlicenseAqualityBmaintenanceAgent-readiness scorecard for any MCP server: protocol checks, 0-100 score and actionable findings.1182 npm1MIT
- AlicenseNot gradedqualityBmaintenanceEnables free, read-only checks of AI agents and MCP servers for conformance, published changes, delivery evidence, and verifiable receipts without requiring an account or API key, using public or non-personal data only.MIT
- AlicenseAqualityBmaintenanceCheck any agent skill or MCP server's security verdict before your agent installs it. Sandbox-based 0-100 verdicts (Verified, Caution, Blocked). Free, read-only, no account.22,274 npmMIT
- AlicenseNot gradedqualityAmaintenanceRuns the MCP initialize handshake and validates tools/list JSON schemas on any public MCP server, and inspects x402 payment endpoints. Ships as a stdio MCP server the agent calls directly, plus a CLI and a GitHub Action. Read-only, no API key needed.133 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.