Skip to content

Compaction-loss audit MCP server

com.textforagents/compaction-loss-audittextforagents.comstreamable-httpv1.0.0Scanned

Compaction witness for agents: pin invariants, name dropped spans, re-inject verbatim or HALT.

4 tools: 1 can delete or cancel things, 2 change things and 1 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel 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 Compaction-loss audit MCP server can do

The Compaction-loss audit MCP server is published by textforagents.com, a domain the MCP Registry verified. It has 4 tools. It can delete or cancel things (1 tool: reinject) and create or change data (2 tools: snapshot and pin). 1 tool only reads.

1 tool brings in text other people can write (audit).

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 10, 2026, version 1.0.0.

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.

4 tools

Deletes or cancels 1Claude Code: deny
  • reinjectrestore DEGRADED/LOST spans verbatim, or HALT on critical loss when allow=false; requires the audit's signed receiptNo 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 destructive (destructiveHint: true).
    Description, as the server wrote it
    restore DEGRADED/LOST spans verbatim, or HALT on critical loss when allow=false; requires the audit's signed receipt

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
Changes things 2Claude Code: ask
  • pinwrite-time pinning: classify + hash-pin ONE span at write timeNo findings

    Why it is in this group

    • The name "pin" says "pin": a word for a change.
    Description, as the server wrote it
    write-time pinning: classify + hash-pin ONE span at write time

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • snapshotpin invariants verbatim pre-compaction (classify + hash-pin spans)No findings

    Why it is in this group

    • The name "snapshot" says "snapshot": a word for reading.
    • The description's first verb is "pin": a word for a change.
    Description, as the server wrote it
    pin invariants verbatim pre-compaction (classify + hash-pin spans)

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
Only reads 1Show 1 read-only tool
  • auditdiff post-compaction context against the pinned snapshot; returns the Ed25519-signed receipt (one metered event)Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "diff": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "diff" and "post": it reads posts, which other people can write.
    Description, as the server wrote it
    diff post-compaction context against the pinned snapshot; returns the Ed25519-signed receipt (one metered event)

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false

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 or outbound.

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 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, 19:21 UTC, unchanged since Oct 29, 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
3
Protocol version
2024-11-05
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 destructive, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://textforagents.com/products/compaction-loss-audit/mcp: tools/list returned 4 tools to an anonymous client, including reinject (destructive), snapshot (write), pin (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. Tools4 changed.~4 changedView diff
    • Changed:auditOnly readstitleannotations
    • Changed:pinChanges thingstitleannotations
    • Changed:reinjectDeletes or cancelstitleannotations
    • Changed:snapshotChanges thingstitleannotations

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http compaction-loss-audit https://textforagents.com/products/compaction-loss-audit/mcp
claude mcp add --transport http compaction-loss-audit https://textforagents.com/products/compaction-loss-audit/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__compaction-loss-audit__audit"
    ],
    "ask": [
      "mcp__compaction-loss-audit__snapshot",
      "mcp__compaction-loss-audit__pin"
    ],
    "deny": [
      "mcp__compaction-loss-audit__reinject"
    ]
  }
}

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 compaction-loss-audit. Review it before you use it.

Capability tags behind 1 rule
  • mcp__compaction-loss-audit__audit 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.textforagents/compaction-loss-audit/verify?hash=bcf0aa571505e4f07946f7f3eed1d0d8ff9f71374889313f49f1dad163a24a2b" | jq -e '.changed == false'

Pinned hash bcf0aa571505, from Nov 10, 2026, 09:17 UTC.

Watch

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

https://radar.anlyon.com/servers/com.textforagents/compaction-loss-audit/changes.xml

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

Badge

Anlyon Radar badge for com.textforagents/compaction-loss-audit
[![Anlyon Radar](https://radar.anlyon.com/badge/com.textforagents/compaction-loss-audit.svg)](https://radar.anlyon.com/servers/com.textforagents/compaction-loss-audit)

Source: MCP Registry. Synced Oct 29, 2026, 02:17 UTC.

Compaction-loss audit MCP server: questions and answers

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

Is the Compaction-loss audit MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 3 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 Compaction-loss audit MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: reinject.

Can the Compaction-loss audit 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 Compaction-loss audit MCP server have?

4 tools: 1 destructive, 2 write, 1 read. reinject, snapshot, pin and audit.

Does the Compaction-loss audit MCP server need sign-in or OAuth?

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

Does the Compaction-loss audit MCP server send data to outside services?

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

Has the Compaction-loss audit MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.