Skip to content

Fittest MCP server

io.github.Pavel-Tk/fittestPavel-Tkstreamable-httpv0.1.1Scanned

Three ML interatomic potentials check a molecule: trust (Beta-posterior score, 90% CI) or DFT.

4 tools: 2 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 2 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • 1 finding

The remote endpoint did not answer the last look. Remote posture

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the Fittest MCP server can do

The Fittest MCP server is published by the GitHub account Pavel-Tk. It has 4 tools. It can create or change data (2 tools: check_structures and usage_stats), but cannot delete data. 2 tools only read.

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

The fixed checks matched 1 finding (long-description). Each one comes with the text it matched.

Last scanned Oct 31, 2026, version 0.1.1.

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.

4 tools

Changes things 2Claude Code: ask
  • check_structuresAsk the Fittest swarm whether a machine-learned interatomic potential can be trusted on your molecular structures, or whether they need DFT.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    Findings

    • Info

      The description is 2,115 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...s, element lists and names are NOT stored. Aggregate counts are public at /stats."

      What this check looks for
    Description, as the server wrote it
    Ask the Fittest swarm whether a machine-learned interatomic potential can be trusted on your molecular structures, or whether they need DFT. Three model agents (MACE-MPA-0, AIMNet2, Orb-v3) predict forces; their disagreement sigma_F and the Calibrator's DFT-label ledger give the verdict. Input `structures`: XYZ text (single or multi-frame; bare 'El x y z' atoms on separate lines or separated by commas/semicolons also work) and/or a list of objects {"Z": [8,1,1] or "symbols": ["O","H","H"], "R": [[x,y,z], ...]} in Angstrom. Exact element symbols only. Limits: <= 20 structures per call, 2..100 atoms each, isolated molecules (no periodic cells). Elements the full committee supports: H B C N O F Si P S Cl As Se Br I. Returns per structure: verdict (trust / send_to_dft) with verdict_reasons, trust_score (Beta posterior P(correct), never exactly 1) with its 90% interval and labels_behind_score, the recommended model or blend, served and reference energy (eV; compare reference_energy_eV across a batch), max/mean force (eV/A), sigma_F vs tau, per-model summary, domain_warning outside C/H/N/O or Transition1x sizes. A bad structure gets its own error entry; the rest are still scored. Rule: trust only if: every model agent supports all elements, the forces do not all vanish, sigma_F < tau, and trust_score >= 0.5. Otherwise send_to_dft, with verdict_reasons. tau is a fixed escalation threshold: the 70th percentile of sigma_F on the round-0 pool. The Calibrator's threshold rule never moved it during the run (see results/RESULTS.md). Logging: every call to this server is logged (UTC time, tool name, an anonymous client id = salted hash of client name + IP), structure and atom counts, verdict counts, latency and ok/error category. Raw IPs are not stored by the app or written to the access log; since 2026-10-31 19:11 UTC Caddy's error/unmapped-host logs drop them too (before that, some Caddy error and bare-IP entries in the system journal contained client IPs, kept until journal rotation). Structures, coordinates, element lists and names are NOT stored. Aggregate counts are public at /stats.
  • usage_statsAggregate usage of this server: distinct users (anonymous clients that got at least one structure verdict; internal test clients excluded), total calls, calls per tool, first/last …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
    Aggregate usage of this server: distinct users (anonymous clients that got at least one structure verdict; internal test clients excluded), total calls, calls per tool, first/last call time. No per-user data. Logging: every call to this server is logged (UTC time, tool name, an anonymous client id = salted hash of client name + IP), structure and atom counts, verdict counts, latency and ok/error category. Raw IPs are not stored by the app or written to the access log; since 2026-10-31 19:11 UTC Caddy's error/unmapped-host logs drop them too (before that, some Caddy error and bare-IP entries in the system journal contained client IPs, kept until journal rotation). Structures, coordinates, element lists and names are NOT stored. Aggregate counts are public at /stats.
Only reads 2Show 2 read-only tools
  • explainExplain why Fittest trusted or escalated ONE structure (XYZ text or {Z|symbols, R}): the verdict rule applied, sigma_F vs tau, the Calibrator bucket with its label count, the poste…No findings

    Why it is in this group

    • The name "explain" says "explain": a word for reading.
    Description, as the server wrote it
    Explain why Fittest trusted or escalated ONE structure (XYZ text or {Z|symbols, R}): the verdict rule applied, sigma_F vs tau, the Calibrator bucket with its label count, the posterior P(correct) of every candidate in it, which model agents disagree most, and the most uncertain atoms. Logging: every call to this server is logged (UTC time, tool name, an anonymous client id = salted hash of client name + IP), structure and atom counts, verdict counts, latency and ok/error category. Raw IPs are not stored by the app or written to the access log; since 2026-10-31 19:11 UTC Caddy's error/unmapped-host logs drop them too (before that, some Caddy error and bare-IP entries in the system journal contained client IPs, kept until journal rotation). Structures, coordinates, element lists and names are NOT stored. Aggregate counts are public at /stats.
  • swarm_statusShow the Fittest population: model agents (answerers) and the Skeptic (critic) with reputations from the ledger, the calibration domain, tau and the verdict rule, which models are …No findings

    Why it is in this group

    • The name "swarm_status" says "status": a word for reading.
    Description, as the server wrote it
    Show the Fittest population: model agents (answerers) and the Skeptic (critic) with reputations from the ledger, the calibration domain, tau and the verdict rule, which models are live, and the evolution family trees if published. Logging: every call to this server is logged (UTC time, tool name, an anonymous client id = salted hash of client name + IP), structure and atom counts, verdict counts, latency and ok/error category. Raw IPs are not stored by the app or written to the access log; since 2026-10-31 19:11 UTC Caddy's error/unmapped-host logs drop them too (before that, some Caddy error and bare-IP entries in the system journal contained client IPs, kept until journal rotation). Structures, coordinates, element lists and names are NOT stored. Aggregate counts are public at /stats.

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.

The remote endpoint did not answer the last look

Looked at Nov 15, 2026, 13:21 UTC, unchanged since Nov 8, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
no
HTTP status of an anonymous initialize
not observed
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: The operation was aborted due to timeout

Posture changes

  1. Nov 8, 2026
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

1 info
  • The description is 2,115 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...s, element lists and names are NOT stored. Aggregate counts are public at /stats."

    What this check looks for

History

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

  1. PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http fittest https://fittest-mcp.westus2.cloudapp.azure.com/mcp
claude mcp add --transport http fittest https://fittest-mcp.westus2.cloudapp.azure.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__fittest__explain",
      "mcp__fittest__swarm_status"
    ],
    "ask": [
      "mcp__fittest__check_structures",
      "mcp__fittest__usage_stats"
    ],
    "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 fittest. 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/io.github.Pavel-Tk/fittest/verify?hash=2f9eddc7e2afa238218192ac2ec945efca05e985c5ab1ae07679c54e6c97a832" | jq -e '.changed == false'

Pinned hash 2f9eddc7e2af, from Oct 31, 2026, 22:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.Pavel-Tk/fittest/changes.xml

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

Badge

Anlyon Radar badge for io.github.Pavel-Tk/fittest
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Pavel-Tk/fittest.svg)](https://radar.anlyon.com/servers/io.github.Pavel-Tk/fittest)

Source: MCP Registry · repository. Synced Oct 31, 2026, 22:17 UTC.

Fittest MCP server: questions and answers

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

Is the Fittest MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Fittest MCP server delete data?

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

Can the Fittest 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 Fittest MCP server have?

4 tools: 2 write, 2 read. check_structures, usage_stats, explain and swarm_status.

Does the Fittest MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Fittest MCP server send data to outside services?

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

Has the Fittest MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Oct 31, 2026.