Eclipse Trust MCP

Verifies Cyan Eclipse benchmark results by checking if they are real, who issued them, their scope, and whether they are anchored on-chain. It serves as a convenience index that provides byte-verbatim verdicts with attached scopes and verify_recipes for independent recomputation from hashes and the chain.

Visit Cyan Eclipse Technologies

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by Cyan Eclipse Technologies

MCP endpoint (Streamable HTTP)

https://cetech.ai/trust/mcp

Vendor documentation

What you can do with it

Verify if a bench result is real and who issued it
Check if a result is anchored on-chain and where
Retrieve validation records and bench verdicts
Resolve agent identities using DID or agent ID

Source and maintenance

Community listingRegistry 0.1.0

mcp-registry: io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/trust@0.1.0 Source repository Project website

Maintenance checked: Nov 1, 2026, 7:10 AM UTC

Protocol and capabilities

Server: eclipse-trust 0.1.0
MCP protocol: 2025-06-18
Tools: 5 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {}
}

Tools

5 advertised

trust_status

Advertised by the server during the last successful anonymous check.

Server health + data provenance: index build time, source recompute checks, verdict/receipt/anchor counts, mainnet vs testnet posture. Call this first to judge freshness.

trust_status input schema

{
  "type": "object",
  "required": [],
  "properties": {}
}

trust_verify_receipt

Advertised by the server during the last successful anonymous check.

Verify a Herald receipt hash: recomputed hash match, the record it belongs to, issuer, anchor state (ANCHORED/PENDING/FAILED/NOT_ENQUEUED) with chain + tx + proof bundle, offline proof verification, and a verify_recipe. Unknown hash returns typed NOT_FOUND.

trust_verify_receipt input schema

{
  "type": "object",
  "required": [],
  "properties": {
    "receipt": {
      "type": "object"
    },
    "receipt_hash": {
      "type": "string"
    }
  }
}

trust_get_bench_verdict

Advertised by the server during the last successful anonymous check.

The current Verity bench verdict for a product, byte-verbatim with scope attached, plus the computed pointer block. No verdict returns typed NO_VERDICT.

trust_get_bench_verdict input schema

{
  "type": "object",
  "required": [
    "product"
  ],
  "properties": {
    "product": {
      "type": "string"
    }
  }
}

trust_get_validation_record

Advertised by the server during the last successful anonymous check.

Resolve an ERC-8004 Validation Registry record by validation_id, request_hash, or product. Testnet records are labelled TESTNET; mainnet lookups return typed NOT_PUBLISHED_MAINNET.

trust_get_validation_record input schema

{
  "type": "object",
  "required": [],
  "properties": {
    "product": {
      "type": "string"
    },
    "request_hash": {
      "type": "string"
    },
    "validation_id": {
      "type": "string"
    }
  }
}

trust_resolve_agent

Advertised by the server during the last successful anonymous check.

Resolve an agent by ERC-8004 agent_id, DID, or registration URL: registration summary plus a trust summary computed from the records at call time.

trust_resolve_agent input schema

{
  "type": "object",
  "required": [],
  "properties": {
    "did": {
      "type": "string"
    },
    "url": {
      "type": "string"
    },
    "agent_id": {
      "type": [
        "string",
        "integer"
      ]
    },
    "identifier": {
      "type": "string"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 123 ms
95th percentile latency: 123 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 7:21 AM UTC · probe · passed · 123 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http eclipse-trust-mcp https://cetech.ai/trust/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add eclipse-trust-mcp --url https://cetech.ai/trust/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable eclipse-trust-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "eclipse-trust-mcp": {
      "url": "https://cetech.ai/trust/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "eclipse-trust-mcp": {
      "type": "streamableHttp",
      "url": "https://cetech.ai/trust/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start eclipse-trust-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "eclipse-trust-mcp": {
      "type": "http",
      "url": "https://cetech.ai/trust/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http eclipse-trust-mcp https://cetech.ai/trust/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "eclipse-trust-mcp": {
      "url": "https://cetech.ai/trust/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "eclipse-trust-mcp": {
      "serverUrl": "https://cetech.ai/trust/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Eclipse Trust MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows