Skip to content

Caelara Labs Agent Safety MCP server

com.caelaralabs/agentcaelaralabs.comstreamable-httpv1.0.1Scanned

Caelara Labs Agent Safety tools over remote MCP. Calls need an X-Caelara-Key API key.

10 tools: 7 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 7 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

7 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 Caelara Labs Agent Safety MCP server can do

The Caelara Labs Agent Safety MCP server is published by caelaralabs.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (7 tools: agent_input_firewall, pii_redactor, prompt_injection_scanner, token_compressor and 3 more), but cannot delete data. 3 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

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 19, 2026, version 1.0.1.

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.

10 tools

Changes things 7Claude Code: ask
  • agent_input_firewallScan untrusted input: injection risk + PII redaction + sanitized text + allow/review/block verdictNo 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
    Scan untrusted input: injection risk + PII redaction + sanitized text + allow/review/block verdict
  • citation_extractorExtract URLs, DOIs, arXiv ids and author-year citationsNo 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
    Extract URLs, DOIs, arXiv ids and author-year citations
  • context_chunkerSplit text into token-bounded overlapping chunksNo 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
    Split text into token-bounded overlapping chunks
  • json_auto_repairRepair malformed JSON from LLM outputNo 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
    Repair malformed JSON from LLM output
  • pii_redactorRedact emails, phones, SSNs, cards (Luhn), IPs, API keys and JWTsNo 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
    Redact emails, phones, SSNs, cards (Luhn), IPs, API keys and JWTs
  • prompt_injection_scannerScore text for prompt-injection patternsNo 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
    Score text for prompt-injection patterns
  • token_compressorCompress text to a target ratio of its original lengthNo 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
    Compress text to a target ratio of its original length
Only reads 3Show 3 read-only tools
  • agent_output_validatorValidate LLM output: repair JSON, enforce schema, check grounding against a source, extract citationsNo findings

    Why it is in this group

    • The description's first verb is "validate": a word for reading.
    Description, as the server wrote it
    Validate LLM output: repair JSON, enforce schema, check grounding against a source, extract citations
  • hallucination_diffFlag answer sentences unsupported by the source textNo findings

    Why it is in this group

    • The name "hallucination_diff" says "diff": a word for reading.
    Description, as the server wrote it
    Flag answer sentences unsupported by the source text
  • schema_enforcerValidate and coerce data to a JSON SchemaNo findings

    Why it is in this group

    • The description's first verb is "validate": a word for reading.
    Description, as the server wrote it
    Validate and coerce data to a JSON Schema

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 untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
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 19, 2026, 17:18 UTC, unchanged since Nov 19, 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
7
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agent.caelaralabs.com/mcp: tools/list returned 10 tools to an anonymous client, including agent_input_firewall (write), pii_redactor (write), prompt_injection_scanner (write), token_compressor (write), json_auto_repair (write) and 2 more

    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 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent https://agent.caelaralabs.com/mcp
claude mcp add --transport http agent https://agent.caelaralabs.com/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__agent__agent_output_validator",
      "mcp__agent__schema_enforcer",
      "mcp__agent__hallucination_diff"
    ],
    "ask": [
      "mcp__agent__agent_input_firewall",
      "mcp__agent__pii_redactor",
      "mcp__agent__prompt_injection_scanner",
      "mcp__agent__token_compressor",
      "mcp__agent__json_auto_repair",
      "mcp__agent__citation_extractor",
      "mcp__agent__context_chunker"
    ],
    "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 agent. Review it before you use it.

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.caelaralabs/agent/verify?hash=f6b91a3aad67cf7d81e41e00e108018a392ede17340f188913e8e9ae8832dc24" | jq -e '.changed == false'

Pinned hash f6b91a3aad67, from Nov 19, 2026, 14:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.caelaralabs/agent/changes.xml

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

Badge

Anlyon Radar badge for com.caelaralabs/agent
[![Anlyon Radar](https://radar.anlyon.com/badge/com.caelaralabs/agent.svg)](https://radar.anlyon.com/servers/com.caelaralabs/agent)

Source: MCP Registry. Synced Nov 19, 2026, 14:17 UTC.

Caelara Labs Agent Safety MCP server: questions and answers

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

Is the Caelara Labs Agent Safety MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 7 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 Caelara Labs Agent Safety MCP server delete data?

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

Can the Caelara Labs Agent Safety 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 Caelara Labs Agent Safety MCP server have?

10 tools: 7 write, 3 read. agent_input_firewall, pii_redactor, prompt_injection_scanner, token_compressor, json_auto_repair, citation_extractor, context_chunker, agent_output_validator and 2 more.

Does the Caelara Labs Agent Safety MCP server need sign-in or OAuth?

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

Does the Caelara Labs Agent Safety MCP server send data to outside services?

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

Has the Caelara Labs Agent Safety MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.