# MCP Verify (remote · verify.sentinelsignal.io)

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

- Trust score: 57/100 (low)
- Change this week: +43
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `verify.sentinelsignal.io`: 57/100 (this document), [markdown](https://verifymcp.io/servers/io-sentinelsignal-verify/verify.md), [page](https://verifymcp.io/servers/io-sentinelsignal-verify/verify)

## Channel facts

- Endpoint: `https://verify.sentinelsignal.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.269`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 22 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1548 tokens (~70/item across 22 items; 22 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 29% of tool parameters carry a description.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http io-sentinelsignal-verify https://verify.sentinelsignal.io/mcp
```

### Codex

```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
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-sentinelsignal-verify --url https://verify.sentinelsignal.io/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-sentinelsignal-verify:
    url: "https://verify.sentinelsignal.io/mcp"
```

### Other

```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 recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 57, +1)

- [functional] Server version: 0.1.0 → 1.0.487

### 2026-08-01 (score 56, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-07-31 (score 56, +42)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 14, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 14, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 14)

First indexed and scored.

## MCP tools (22)

### `search` (~69 tokens)

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

Input parameters:

- `limit` (integer): Maximum number of search results to return.
- `query` (string, required): Search query such as healthcare MCP, web search MCP, ChatGPT-compatible MCPs, or OAuth MCP servers.

### `fetch` (~49 tokens)

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

Input parameters:

- `id` (string, required): Canonical MCP server identifier in namespace/name format.

### `search_servers` (~144 tokens)

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

Input parameters:

- `auth_preference` (string): Preferred auth mode. Use unauthenticated when the agent must avoid login flows.
- `capabilities` (array): Normalized capability taxonomy terms such as healthcare, search, read, exec, files, oauth, or prompts.
- `client_target` (string): Optional target client or integration surface.
- `limit` (integer): Maximum number of ranked candidates to return.
- `query` (string): Optional free-text query to bias ranking toward a specific use case or domain.
- `risk_tolerance` (string): How much tool-surface risk is acceptable.

### `recommend_servers` (~125 tokens)

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

Input parameters:

- `auth_preference` (string): Preferred auth mode.
- `capabilities` (array): Optional explicit capability constraints that override or extend the inferred task capabilities.
- `client_target` (string): Optional target client or integration surface.
- `limit` (integer): Maximum number of recommendations to return.
- `risk_tolerance` (string): How much tool-surface risk is acceptable.
- `task` (string, required): Plain-language task description such as 'I need an MCP for healthcare denial scoring in OpenAI connectors'.

### `get_server_report` (~38 tokens)

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

Input parameters:

- `identifier` (string, required): Canonical server identifier in namespace/name format.

### `compare_servers` (~48 tokens)

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

Input parameters:

- `identifiers` (array, required): Canonical server identifiers in namespace/name format.

### `route_task` (~132 tokens)

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

Input parameters:

- `candidate` (string): Optional namespace/name server identifier to evaluate directly.
- `capabilities` (array): Optional capability constraints such as healthcare, search, database, read, or write.
- `client_target` (string)
- `max_freshness_hours` (number)
- `max_risk` (string): Maximum allowed tool risk.
- `no_write_without_approval` (boolean)
- `requires_oauth` (boolean)
- `task` (string, required): Task the agent wants to perform.

### `decide_agent_call` (~199 tokens)

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.

Input parameters:

- `action` (string)
- `agent_id` (string, required)
- `approval_token_present` (boolean)
- `audit_context` (object)
- `client` (string)
- `mandate_id` (string): Optional Verify Mandate key or id.
- `max_cost` (number)
- `max_freshness_hours` (number)
- `max_risk` (string)
- `max_runtime_seconds` (integer)
- `no_write_without_approval` (boolean)
- `payload_classification` (array)
- `requested_cost` (number)
- `requires_oauth` (boolean)
- `server_id` (string, required): Server identifier in namespace/name format.
- `tool` (string, required)
- `user_id` (string, required)

### `create_mandate` (~114 tokens)

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

Input parameters:

- `agent_id` (string, required)
- `budget_limit` (number)
- `constraints` (object)
- `metadata` (object)
- `requires_human_approval` (boolean)
- `scope` (string, required)
- `server_id` (string)
- `signature` (string)
- `user_id` (string, required)
- `valid_until` (string)

### `get_evidence_pack` (~66 tokens)

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

Input parameters:

- `agent_id` (string)
- `limit` (integer)
- `server_id` (string)
- `user_id` (string)

### `compile_docs` (~120 tokens)

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

Input parameters:

- `markdown_docs` (string)
- `metadata` (object)
- `openapi_spec` (object)
- `policy_metadata` (object)
- `postman_collection` (object)
- `server_identifier` (string)
- `source_type` (string)
- `source_url` (string)
- `title` (string, required)
- `website_docs` (string)

### `export_policy` (~95 tokens)

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

Input parameters:

- `client` (string)
- `identifier` (string, required): Canonical server identifier in namespace/name format.
- `max_freshness_hours` (number)
- `max_risk` (string)
- `no_write_without_approval` (boolean)
- `requires_oauth` (boolean)

### `get_subscription_options` (~24 tokens)

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

### `get_gateway_options` (~39 tokens)

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

### `get_hosting_options` (~25 tokens)

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

### `list_agents` (~46 tokens)

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

Input parameters:

- `limit` (integer)
- `risk_level` (string)

### `get_agent` (~38 tokens)

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

Input parameters:

- `agent_id` (string, required)

### `score_agent` (~39 tokens)

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

Input parameters:

- `agent` (object)
- `agent_id` (string)

### `explain_agent_risk` (~35 tokens)

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

Input parameters:

- `agent_id` (string, required)

### `list_high_risk_agents` (~32 tokens)

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

Input parameters:

- `limit` (integer)

### `get_drift_report` (~38 tokens)

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

Input parameters:

- `agent_id` (string)
- `limit` (integer)

### `generate_remediation_plan` (~33 tokens)

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

Input parameters:

- `agent_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-sentinelsignal-verify/verify#diagnostics

## Score history

- 2026-08-03: 57
- 2026-08-02: 57
- 2026-08-01: 56
- 2026-07-31: 56
- 2026-07-30: 14
- 2026-07-29: 14
- 2026-07-28: 14
- 2026-07-27: 14
- 2026-07-26: 14

## Links

- Remote endpoint: https://verify.sentinelsignal.io/mcp
- Website: https://verify.sentinelsignal.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-sentinelsignal-verify/verify/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-sentinelsignal-verify/verify/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-sentinelsignal-verify/verify