protogrid
Sign inAdd to your agent

Search / com.textforagents/compaction-loss-audit

Compaction-loss audit

R0· no sign-in

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

v1.0.0 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality85good
Trust83of 100
Uptime, 30 days100%
Latency p5073 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "compaction-loss-audit": {
      "type": "http",
      "url": "https://textforagents.com/products/compaction-loss-audit/mcp"
    }
  }
}
claude mcp add --transport http compaction-loss-audit https://textforagents.com/products/compaction-loss-audit/mcp
[mcp_servers.compaction-loss-audit]
url = "https://textforagents.com/products/compaction-loss-audit/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "compaction-loss-audit": {
      "type": "remote",
      "url": "https://textforagents.com/products/compaction-loss-audit/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "compaction-loss-audit": {
      "type": "http",
      "url": "https://textforagents.com/products/compaction-loss-audit/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=compaction-loss-audit&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdGV4dGZvcmFnZW50cy5jb20vcHJvZHVjdHMvY29tcGFjdGlvbi1sb3NzLWF1ZGl0L21jcCJ9"
}
{
  "servers": {
    "compaction-loss-audit": {
      "type": "http",
      "url": "https://textforagents.com/products/compaction-loss-audit/mcp"
    }
  }
}
{
  "mcpServers": {
    "compaction-loss-audit": {
      "httpUrl": "https://textforagents.com/products/compaction-loss-audit/mcp"
    }
  }
}
extensions:
  "compaction-loss-audit":
    enabled: true
    name: "compaction-loss-audit"
    type: streamable_http
    uri: "https://textforagents.com/products/compaction-loss-audit/mcp"
    timeout: 300

Quality 85 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations4 of 4 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: pin (idempotentHint, openWorldHint); audit (idempotentHint, openWorldHint); reinject (idempotentHint, openWorldHint); …
  • pass
    tools.token_costabout 315 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changes4 tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

4 tools, about 315 tokens to load them all · tool set a4c40eca0436 · tools last changed 2026-11-03 · checked 2026-11-07 17:28 UTC

Tool changes

  • reinjectchangedtitle, annotations
  • auditchangedtitle, annotations
  • pinchangedtitle, annotations
  • snapshotchangedtitle, annotations

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository
provenance55
liveness100
freshness100
hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-10d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://textforagents.com/products/compaction-loss-audit/mcp streamable-httpnoneyes100%73 ms2024-11-052026-11-07

Tools (4)

auditread-onlydiff post-compaction context against the pinned snapshot; returns the Ed25519-signed receipt (one metered event)
pinwrite-time pinning: classify + hash-pin ONE span at write time
reinjectdestructiverestore DEGRADED/LOST spans verbatim, or HALT on critical loss when allow=false; requires the audit's signed receipt
snapshotpin invariants verbatim pre-compaction (classify + hash-pin spans)

Schemas: list_tools.

Similar MCP servers

  • inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trailL0
    io.github.DanceNitra/inspeximus

    Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.

  • lcc — Local Context CompilerL0
    io.github.lucasmartins-ai/lcc

    Compact agent context verbatim, offline: cut spent tool outputs, recall them by hash.

  • SnapbackR0quality 91
    io.github.ra1labsworkx-wq/snapback

    Diagnose why an AI agent failed and get the verified fix instantly. Free, no token.

  • lossless-context-mcpL0
    io.github.NORTHTEKDevs/lossless-context-mcp

    Agent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts.

  • OffenseR0quality 91
    io.github.offense-research/offense

    Security tools for coding agents: dependency advisory audits and evidence for remediation.

  • rubrkitR0quality 79
    com.rubrkit/rubrkit

    MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.

More from com.textforagents

  • Futility BreakerR0quality 80
    com.textforagents/futility-breaker-evidence-bound-stopping

    Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts.

  • Outcome-verified watchdog for scheduled agentsR0quality 80
    com.textforagents/scheduled-agent-outcome-verification

    Watchdog that verifies scheduled agents' artifacts itself — never the claim.

  • Agent Access Door CheckR0quality 79
    com.textforagents/agent-access-door-check

    Before your agent sets out, ask whether the site will let it in

  • Agent-asset reclamation (lost-and-found)R0quality 79
    com.textforagents/agent-asset-reclamation-lost-and-found

    Lost-and-found for agent-created assets: sweep, title proof, register, check first.

  • Agent-Carried Work HistoryR0quality 79
    com.textforagents/agent-carried-work-history

    Your agent carries its own resume — outcome receipts minted at settlement, held by the agent.

  • Agent Continuity BondR0quality 79
    com.textforagents/agent-continuity-bond

    Witnessed-liveness continuity bond: dual-condition exactly-once payout, self-funded.

And 124 more from this publisher.

Official server.json
{
  "name": "com.textforagents/compaction-loss-audit",
  "title": "Compaction-loss audit",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://textforagents.com/products/compaction-loss-audit/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://textforagents.com/products/compaction-loss-audit/",
  "description": "Compaction witness for agents: pin invariants, name dropped spans, re-inject verbatim or HALT."
}