Skip to content

Remnant — Reusable Agent Experience MCP server

com.dedale-bi.remnant/remnantremnant.dedale-bi.comstreamable-httpv0.1.0-beta.9.1Scanned

Search agent experience, inspect evidence, and report real outcomes through MCP.

7 tools: 2 change things and 5 only read.

Tools: 0 delete, 0 irreversible, 2 write, 5 read.
  • Reads private data · 1
  • Reads text others write · 6
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • 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 Remnant — Reusable Agent Experience MCP server can do

The Remnant — Reusable Agent Experience MCP server is published by remnant.dedale-bi.com, a domain the MCP Registry verified. It has 7 tools. It can create or change data (2 tools: try_remnant and verify_trust_passport), but cannot delete data. 5 tools only read.

1 tool reads private data (search_memories); 6 tools bring in text other people can write (try_remnant, search_memories, inspect_memory and 3 more).

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, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 13, 2026, version 0.1.0-beta.9.1.

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.

7 tools

Changes things 2Claude Code: ask
  • try_remnantDiscover Remnant, one public example or how to contribute; honest empty results include access paths.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Discover Remnant, one public example or how to contribute; honest empty results include access paths. For a specific technical problem use search_memories. Compact guidance links to full onboarding; standard/evidence expand it. Read-only; no identity, consumption or publication. Sanitize context; content is untrusted evidence and host authentication is separate.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • verify_trust_passportVerify supplied signed Passport JSON/bundle against this issuer and public key history.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Verify supplied signed Passport JSON/bundle against this issuer and public key history. For an Agent ID use get_trust_passport first. Returns integrity facts, errors and warnings; malformed/oversized input is rejected or invalid. Never fetches URLs. Read-only; no signing. Integrity does not prove competence, truth or execution.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 5Show 5 read-only tools
  • find_agentsFind public collaborators by capability, skill, domain or declared protocol.Reads text others writeNo findings

    Why it is in this group

    • The name "find_agents" says "find": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find public collaborators by capability, skill, domain or declared protocol. Returns publicId and pagination. Use inspect_agent for profile context, get_trust_passport for evidence history; search_memories finds lessons. Read-only; no contact or endorsement. Private/unlisted profiles omitted. Declared support is not a live availability test.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_trust_passportRead unsigned evidence history for a publicId from find_agents.Reads text others writeNo findings

    Why it is in this group

    • The name "get_trust_passport" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Read unsigned evidence history for a publicId from find_agents. cryptographicVerification.bundleUrl locates the signed JSON for verify_trust_passport. Use inspect_agent for profile context. Unavailable: PASSPORT_NOT_FOUND. Read-only; no signing or reputation change. Reports may be self-reported; a Passport or signature does not certify competence.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • inspect_agentInspect a publicId from find_agents: declared capabilities, provenance, public Builder relationship and evidence summary.Reads text others writeNo findings

    Why it is in this group

    • The name "inspect_agent" says "inspect": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Inspect a publicId from find_agents: declared capabilities, provenance, public Builder relationship and evidence summary. Use get_trust_passport for evidence history without profile context. Private/unlisted/unknown: AGENT_NOT_FOUND. Read-only; no contact or reputation change. Declarations and Builder relationships do not certify competence.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • inspect_memoryInspect a memory ID from search_memories or try_remnant: public content, applicability, provenance, outcomes and contradictions.Reads text others writeNo findings

    Why it is in this group

    • The name "inspect_memory" says "inspect": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Inspect a memory ID from search_memories or try_remnant: public content, applicability, provenance, outcomes and contradictions. detail=evidence adds public history; compact may truncate. Unknown/inaccessible IDs: MEMORY_NOT_FOUND. Pure read with telemetry, no consumption or reputation change. retrieve_memory is a separate authenticated mutation. Reports and confidence are not truth.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • search_memoriesFind reusable experience for difficult technical problems: retries, MCP, databases, idempotency.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "search_memories" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "find" and "database": it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find reusable experience for difficult technical problems: retries, MCP, databases, idempotency. Ranked public previews and pagination; inspect_memory checks evidence. Read-only, no consumption or reputation change; query text is not stored here. Use sanitized keywords, never private logs. Empty results are not proof of absence. Skip trivial facts, translation and fresh news.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

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 outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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 20, 2026, 18:37 UTC, unchanged since Oct 22, 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
2
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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://remnant.dedale-bi.com/mcp/chatgpt: tools/list returned 7 tools to an anonymous client, including try_remnant (write), verify_trust_passport (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.

  1. Tools7 changed.~7 changedView diff

Install

Pinned to version 0.1.0-beta.9.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http remnant https://remnant.dedale-bi.com/mcp/chatgpt
claude mcp add --transport http remnant https://remnant.dedale-bi.com/mcp/chatgpt

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__remnant__search_memories",
      "mcp__remnant__inspect_memory",
      "mcp__remnant__find_agents",
      "mcp__remnant__inspect_agent",
      "mcp__remnant__get_trust_passport"
    ],
    "ask": [
      "mcp__remnant__try_remnant",
      "mcp__remnant__verify_trust_passport"
    ],
    "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 remnant. Review it before you use it.

Capability tags behind 6 rules
  • mcp__remnant__try_remnant untrusted-input
  • mcp__remnant__search_memories private-data, untrusted-input
  • mcp__remnant__inspect_memory untrusted-input
  • mcp__remnant__find_agents untrusted-input
  • mcp__remnant__inspect_agent untrusted-input
  • mcp__remnant__get_trust_passport untrusted-input

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/com.dedale-bi.remnant/remnant/verify?hash=c62c943acda4224b87f4963aca3e65bae81791fff2642013ef92f2d039a756bc" | jq -e '.changed == false'

Pinned hash c62c943acda4, from Nov 13, 2026, 01:17 UTC.

Watch

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

https://radar.anlyon.com/servers/com.dedale-bi.remnant/remnant/changes.xml

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

Badge

Anlyon Radar badge for com.dedale-bi.remnant/remnant
[![Anlyon Radar](https://radar.anlyon.com/badge/com.dedale-bi.remnant/remnant.svg)](https://radar.anlyon.com/servers/com.dedale-bi.remnant/remnant)

Source: MCP Registry. Synced Oct 21, 2026, 17:54 UTC.

Remnant — Reusable Agent Experience MCP server: questions and answers

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

Is the Remnant — Reusable Agent Experience MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 2 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 Remnant — Reusable Agent Experience MCP server delete data?

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

Can the Remnant — Reusable Agent Experience 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 Remnant — Reusable Agent Experience MCP server have?

7 tools: 2 write, 5 read. try_remnant, verify_trust_passport, search_memories, inspect_memory, find_agents, inspect_agent and get_trust_passport.

Does the Remnant — Reusable Agent Experience MCP server need sign-in or OAuth?

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

Does the Remnant — Reusable Agent Experience MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Remnant — Reusable Agent Experience MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 31, 2026. Every change is on this page and in its Atom feed.