Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

MCP Verify

REMOTE · VERIFY.SENTINELSIGNAL.IO · SCANNED SEP 22

Trust, freshness, policy, and discovery layer for public MCP servers.

0 this week 75 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1548 tokens (~70/item across 22 items; 22 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage76
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 29% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
  • Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the MCP Verify server?

MCP Verify is a hosted endpoint at https://verify.sentinelsignal.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · verify.sentinelsignal.io

# add to Claude Code
claude mcp add --transport http io-sentinelsignal-verify 'https://verify.sentinelsignal.io/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "io-sentinelsignal-verify": {
      "url": "https://verify.sentinelsignal.io/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "io-sentinelsignal-verify": {
      "type": "http",
      "url": "https://verify.sentinelsignal.io/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.io-sentinelsignal-verify]
url = "https://verify.sentinelsignal.io/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-sentinelsignal-verify": {
      "type": "remote",
      "url": "https://verify.sentinelsignal.io/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add io-sentinelsignal-verify --url 'https://verify.sentinelsignal.io/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  io-sentinelsignal-verify:
    url: "https://verify.sentinelsignal.io/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "io-sentinelsignal-verify": {
      "Transport": "http",
      "Url": "https://verify.sentinelsignal.io/mcp"
    }
  }
}
# add to Vellum
assistant mcp add io-sentinelsignal-verify -t streamable-http -u 'https://verify.sentinelsignal.io/mcp'
// mcp.json
{
  "mcpServers": {
    "io-sentinelsignal-verify": {
      "type": "http",
      "url": "https://verify.sentinelsignal.io/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 22 Sept 26 0
    • Server version: 1.0.818 → 1.0.819 functional
  • 20 Sept 26 0
    • Server version: 1.0.811 → 1.0.818 functional
  • 8 Sept 26 0
    • Server version: 1.0.806 → 1.0.811 functional
  • 7 Sept 26 0
    • Server version: 1.0.796 → 1.0.806 functional
  • 6 Sept 26 0
    • Server version: 1.0.775 → 1.0.796 functional
  • 4 Sept 26 0
    • Server version: 1.0.773 → 1.0.775 functional
  • 3 Sept 26 0
    • Server version: 1.0.771 → 1.0.773 functional
  • 2 Sept 26 0
    • Server version: 1.0.762 → 1.0.771 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 22 Sept 2026 · Probed https://verify.sentinelsignal.io/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=verify.sentinelsignal.io CN=YE2,O=Let's Encrypt,C=US 31 Jul 2026 29 Oct 2026 ECDSA 256 ECDSA-SHA384 6217a1383c6dde18e5006fc025671e2ed63
SANs: verify.sentinelsignal.io
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of verify.sentinelsignal.io. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
io. present 57355 8 Verified
sentinelsignal.io. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://verify.sentinelsignal.io/mcp Verified 200
http (plaintext) http://verify.sentinelsignal.io/mcp HTTPS enforced 308 https://verify.sentinelsignal.io/mcp
MCP tools · 22 exposed · ~1,548 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compare_servers ~48

Compare up to four MCP servers side by side across score, verdict, auth, tool count, prompts/resources, and freshness.

NameTypeReqDescription
identifiersarrayyesCanonical server identifiers in namespace/name format.

No output schema declared.

No examples provided.

compile_docs ~120

Generate agent-readable MCP artifacts from product docs: server card, llms.txt, tool schemas, examples, policy metadata, score preview, and hosted docs page.

NameTypeReqDescription
markdown_docsstring
metadataobject
openapi_specobject
policy_metadataobject
postman_collectionobject
server_identifierstring
source_typestring
source_urlstring
titlestringyes
website_docsstring

No output schema declared.

No examples provided.

create_mandate ~114

Create a Verify Mandate: signed delegated authority for an agent/user/server scope, budget, validity window, and tool constraints.

NameTypeReqDescription
agent_idstringyes
budget_limitnumber
constraintsobject
metadataobject
requires_human_approvalboolean
scopestringyes
server_idstring
signaturestring
user_idstringyes
valid_untilstring

No output schema declared.

No examples provided.

decide_agent_call ~199

Verify Gateway decision point. Decide whether this agent may call this tool, with this payload, for this user, right now. Writes an audit-ledger decision event.

NameTypeReqDescription
actionstring
agent_idstringyes
approval_token_presentboolean
audit_contextobject
clientstring
mandate_idstringOptional Verify Mandate key or id.
max_costnumber
max_freshness_hoursnumber
max_riskstring
max_runtime_secondsinteger
no_write_without_approvalboolean
payload_classificationarray
requested_costnumber
requires_oauthboolean
server_idstringyesServer identifier in namespace/name format.
toolstringyes
user_idstringyes

No output schema declared.

No examples provided.

explain_agent_risk ~35

Agent Sprawl Radar: explain risk findings and the recommended action for one registry agent.

NameTypeReqDescription
agent_idstringyes

No output schema declared.

No examples provided.

export_policy ~95

Export a JSON TrustOps policy for one MCP server with allow, blocked tools, required scopes, freshness, and approval gates.

NameTypeReqDescription
clientstring
identifierstringyesCanonical server identifier in namespace/name format.
max_freshness_hoursnumber
max_riskstring
no_write_without_approvalboolean
requires_oauthboolean

No output schema declared.

No examples provided.

fetch ~49

ChatGPT-compatible read-only fetch alias. Returns a full MCP server item with id, title, text, url, and metadata.

NameTypeReqDescription
idstringyesCanonical MCP server identifier in namespace/name format.

No output schema declared.

No examples provided.

generate_remediation_plan ~33

Agent Sprawl Radar: generate deterministic remediation steps for risky or drifting agents.

NameTypeReqDescription
agent_idstringyes

No output schema declared.

No examples provided.

get_agent ~38

Agent Sprawl Radar: return one agent with tools, data access, findings, drift, and recommended action.

NameTypeReqDescription
agent_idstringyes

No output schema declared.

No examples provided.

get_drift_report ~38

Agent Sprawl Radar: return agent drift events across latest snapshots.

NameTypeReqDescription
agent_idstring
limitinteger

No output schema declared.

No examples provided.

get_evidence_pack ~66

Return Verify Ledger evidence packs with invocations, hash-chained audit events, decisions, outcomes, mandates, and cost summaries.

NameTypeReqDescription
agent_idstring
limitinteger
server_idstring
user_idstring

No output schema declared.

No examples provided.

get_gateway_options ~39

Return Verify Gateway semantics, /v1/route versus /v1/decide guidance, mandate inputs, ledger evidence hooks, and decision fields.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_hosting_options ~25

Return Verify Hosted MCP runtime/sandbox hosting capabilities, controls, and endpoints.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_server_report ~38

Return the full machine-readable verify report for a specific MCP server identifier.

NameTypeReqDescription
identifierstringyesCanonical server identifier in namespace/name format.

No output schema declared.

No examples provided.

get_subscription_options ~24

Return alert types, subscription channels, watch scopes, and existing subscription endpoints.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_agents ~46

Agent Sprawl Radar: list discovered AI agents, MCP servers, bots, workflows, risk levels, and owners.

NameTypeReqDescription
limitinteger
risk_levelstring

No output schema declared.

No examples provided.

list_high_risk_agents ~32

Agent Sprawl Radar: list high and critical risk agents for review.

NameTypeReqDescription
limitinteger

No output schema declared.

No examples provided.

recommend_servers ~125

Recommend MCP servers for a plain-language task and return ranked matches with install config.

NameTypeReqDescription
auth_preferencestringPreferred auth mode.
capabilitiesarrayOptional explicit capability constraints that override or extend the inferred task capabilities.
client_targetstringOptional target client or integration surface.
limitintegerMaximum number of recommendations to return.
risk_tolerancestringHow much tool-surface risk is acceptable.
taskstringyesPlain-language task description such as 'I need an MCP for healthcare denial scoring in OpenAI connectors'.

No output schema declared.

No examples provided.

route_task ~132

Choose the best MCP server/tools for a task. Use decide_agent_call when evaluating one specific attempted tool call.

NameTypeReqDescription
candidatestringOptional namespace/name server identifier to evaluate directly.
capabilitiesarrayOptional capability constraints such as healthcare, search, database, read, or write.
client_targetstring
max_freshness_hoursnumber
max_riskstringMaximum allowed tool risk.
no_write_without_approvalboolean
requires_oauthboolean
taskstringyesTask the agent wants to perform.

No output schema declared.

No examples provided.

score_agent ~39

Agent Sprawl Radar: score a normalized agent payload or an existing registry agent.

NameTypeReqDescription
agentobject
agent_idstring

No output schema declared.

No examples provided.

search ~69

ChatGPT-compatible read-only search alias. Returns MCP server results with id, title, and url.

NameTypeReqDescription
limitintegerMaximum number of search results to return.
querystringyesSearch query such as healthcare MCP, web search MCP, ChatGPT-compatible MCPs, or OAuth MCP servers.

No output schema declared.

No examples provided.

search_servers ~144

Search and rank MCP servers by capability, auth preference, client target, and risk tolerance.

NameTypeReqDescription
auth_preferencestringPreferred auth mode. Use unauthenticated when the agent must avoid login flows.
capabilitiesarrayNormalized capability taxonomy terms such as healthcare, search, read, exec, files, oauth, or prompts.
client_targetstringOptional target client or integration surface.
limitintegerMaximum number of ranked candidates to return.
querystringOptional free-text query to bias ranking toward a specific use case or domain.
risk_tolerancestringHow much tool-surface risk is acceptable.

No output schema declared.

No examples provided.

Common questions

What is the MCP Verify server?

MCP Verify is listed in the public MCP registry as io.sentinelsignal/verify. Trust, freshness, policy, and discovery layer for public MCP servers. This page covers its hosted endpoint (https://verify.sentinelsignal.io/mcp).

Is the MCP Verify server safe to use?

MCP Verify scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the MCP Verify server expose?

MCP Verify exposes 22 tools: search, fetch, search_servers, recommend_servers, get_server_report, and 17 more. Their descriptions and schemas cost roughly 1,548 tokens of context every time the server is loaded.

Does the MCP Verify server require authentication?

No. We connected to MCP Verify without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the MCP Verify server still maintained?

MCP Verify is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.