Skip to content

Eclipse Trust MCP server

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/trustCYAN-ECLIPSE-TECHNOLOGIES-LLCstreamable-httpv0.1.0Scanned

Is this bench result real? Who issued it, at what scope, anchored where? One call answers.

5 tools: 1 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 1 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Eclipse Trust MCP server can do

The Eclipse Trust MCP server is published by the GitHub account CYAN-ECLIPSE-TECHNOLOGIES-LLC. It has 5 tools. It can create or change data (1 tool: trust_verify_receipt), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (trust_resolve_agent); 1 tool can send data out of your system (trust_resolve_agent).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 9, 2026, version 0.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Changes things 1Claude Code: ask
  • trust_verify_receiptVerify 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 p…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
Only reads 4Show 4 read-only tools
  • trust_get_bench_verdictThe current Verity bench verdict for a product, byte-verbatim with scope attached, plus the computed pointer block.No findings

    Why it is in this group

    • The name "trust_get_bench_verdict" says "get": a word for reading.
    Description, as the server wrote it
    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_validation_recordResolve an ERC-8004 Validation Registry record by validation_id, request_hash, or product.No findings

    Why it is in this group

    • The name "trust_get_validation_record" says "get": a word for reading.
    Description, as the server wrote it
    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_resolve_agentResolve an agent by ERC-8004 agent_id, DID, or registration URL: registration summary plus a trust summary computed from the records at call time.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "trust_resolve_agent" says "resolve": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "resolve" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    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_statusServer health + data provenance: index build time, source recompute checks, verdict/receipt/anchor counts, mainnet vs testnet posture.No findings

    Why it is in this group

    • The name "trust_status" says "status": a word for reading.
    Description, as the server wrote it
    Server health + data provenance: index build time, source recompute checks, verdict/receipt/anchor counts, mainnet vs testnet posture. Call this first to judge freshness.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 18, 2026, 16:24 UTC, unchanged since Oct 27, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://cetech.ai/trust/mcp: tools/list returned 5 tools to an anonymous client, including trust_verify_receipt (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__trust__trust_status",
      "mcp__trust__trust_get_bench_verdict",
      "mcp__trust__trust_get_validation_record"
    ],
    "ask": [
      "mcp__trust__trust_verify_receipt",
      "mcp__trust__trust_resolve_agent"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as trust. Review it before you use it.

Capability tags behind 1 rule
  • mcp__trust__trust_resolve_agent untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/trust/verify?hash=b89cf724a18d3c00cdca9127c2b44b893337acce72fdf5162c68725edaebfe41" | jq -e '.changed == false'

Pinned hash b89cf724a18d, from Nov 9, 2026, 17:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/trust/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/trust
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/trust.svg)](https://radar.anlyon.com/servers/io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/trust)

Source: MCP Registry · repository. Synced Oct 27, 2026, 18:17 UTC.

Eclipse Trust MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Eclipse Trust MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Eclipse Trust MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Eclipse Trust MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Eclipse Trust MCP server have?

5 tools: 1 write, 4 read. trust_verify_receipt, trust_status, trust_get_bench_verdict, trust_get_validation_record and trust_resolve_agent.

Does the Eclipse Trust MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Eclipse Trust MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): trust_resolve_agent.

Has the Eclipse Trust MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.