MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

ai.qompass/fathom

Reverse-engineering tools for agents over MCP/A2A, with evidence-carrying findings. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-10-23Topic: developer-tools · AI-classifiedversion 0.1.1Ruststandard input/output25 tools

Summary

ai.qompass/fathom is a local MCP server listed in the official MCP registry at version 0.1.1. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 25 tools, 0 resources and 0 prompts.

Record checks

4 of 5 record checks met · 4 do not apply

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
not met: Repository publishes a security policy (SECURITY.md)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: not an npm or PyPI package
Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: local package
Transport: standard input/output
Package: MCP bundle
Repository: public
Tools: 25
Described as changing data: 4 of 25 toolsAI-classified
Topic: developer-toolsAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

4 tools are described as changing something (apply_style_via_lumen, capture_process, export_evidence_bundle, …): our AI model's reading of the descriptions, not something we tested. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested

yes, a real session (not a text-only review)

Last tested

2026-10-23

Mode

read-only (no tool calls)

Latest version

0.1.1, published 2026-10-19 (registry, as of the 2026-10-23 snapshot)

First listed version

2026-10-19 (earliest version still in the registry; older removed versions would be earlier)

Version history

2 versions listed, all on 2026-10-19; 2 in the 90 days before the 2026-10-23 snapshot.

Most recent 2 versions

0.1.1 · 2026-10-19
0.1.0 · 2026-10-19

(versions still listed in the registry only)

Registry data

snapshot 2026-10-23

Package and repository

checked 2026-10-22

Engine

mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.1.1 (published 2026-10-19).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

25tools

0resources

0prompts

4 of 25 tools are described as changing something (creating, editing, deleting, sending or running).

analyze_art_stylereads or searches
“Measured style spec of an image or GIF: palette, grade statistics, shading model, animation timing grammar, sheet geometry”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
- palette_colorsinteger“Palette clusters to extract (default 8)”
- targetstringrequired“Path under a configured target root”
analyze_functionreads or searches
“Function dossier: listing, bounded decompile, callers, callees”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 2 required
- functionstringrequired
- targetstringrequired
analyze_javascript_applicationreads or searches
“Static analysis of a JS/Electron application: modules, graph, IPC boundaries”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
apply_style_via_lumencreates or changes datadescribed as changing data
“Grade an image with lumen's style engine (stdio MCP style_apply) and verify the output against an optional reference style spec”
Publisher declares: read-only no · destructive no · open-world no
6 inputs, 4 required
- lumen_programstringrequired“Lumen binary name; must be in allow_programs”
- outputstringrequired“Output file name (.png), written under the state dir”
- presetstringrequired“Lumen style preset name (see lumen style_list)”
- referencestring“Optional art target whose style spec the output is verified against”
- strengthnumber“Grade strength (default 1.0)”
- targetstringrequired“Path under a configured target root”
binary_overviewreads or searches
“Program identity, memory map, and inventory counts”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
capture_processruns code or commandsdescribed as changing data
“Run an allowlisted command confined, capturing output, exit, timing, and hashes”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- commandarrayrequired“argv; the program must be allowlisted by name in config”
compare_artifactsreads or searches
“Compare two artifacts: identity, sizes, and byte equality”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 2 required
- astringrequired
- bstringrequired
export_evidence_bundlecreates or changes datadescribed as changing data
“Package evidence envelopes into a digest-sealed bundle”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- resultsarrayrequired
inspect_android_apkreads or searches
“Static APK inventory: ZIP contents, contents classes, and the binary-XML manifest (package, permissions, components)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
inspect_artifactreads or searches
“File identity and classification, or a bounded directory inventory”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
inspect_asarreads or searches
“ASAR archive inventory: entries, sizes, offsets, unpacked flags”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
inspect_binary_layoutreads or searches
“Container layout and mitigation candidates, read directly (no engine)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”

Show 13 more tools

inspect_evm_bytecodereads or searches
“Offline EVM bytecode: dispatcher scan and inferred function selectors”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- bytecodestring“Hex bytecode, optional 0x prefix”
- targetstring“Or a file under a target root”
inspect_firmwarereads or searches
“Firmware inspection: header/format detection, embedded-filesystem signature scan, entropy profile (no extraction)”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
inspect_managed_assemblyreads or searches
“.NET metadata inventory: identity, types, methods, P/Invoke, signature digests”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
inspect_source_mapreads or searches
“Source-map v3 parsing: sources, sourcesContent presence, segments, and generated-to-original position mapping”
Publisher declares: read-only yes · destructive no · open-world no
3 inputs, 1 required
- generated_columninteger
- generated_lineinteger
- targetstringrequired“Path to a .map file under a configured target root”
inspect_web_capturereads or searches
“HAR capture reading: request/response inventory and payload exposure”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
list_functionson 4 other serversreads or searches
“Function inventory with classifications and signatures”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
list_nameson 2 other serversreads or searches
“Symbol inventory: addresses, names, types”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
list_stringsreads or searches
“Defined-string inventory with addresses”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- targetstringrequired“Path under a configured target root”
observe_browsercontrols a browser or desktop
“Chromium-headless page observation: title, meta, script, link, and form inventory from the serialized DOM”
Publisher declares: read-only no · destructive no · open-world no
1 input, 1 required
- urlstringrequired
remap_palettecreates or changes datadescribed as changing data
“Native deterministic palette remap of an image (nearest or exact) to a supplied palette or another asset's measured palette”
Publisher declares: read-only no · destructive no · open-world no
5 inputs, 2 required
- modestring“Default nearest”
- outputstringrequired“Output file name (.png), written under the state dir”
- palettearray“#RRGGBB entries (1..=256); mutually exclusive with palette_from”
- palette_fromstring“Art target whose measured palette to use”
- targetstringrequired“Path under a configured target root”
search_inventoryon 13 other serversreads or searches
“Substring search across functions, symbols, and strings”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 2 required
- querystringrequired
- targetstringrequired
session_infoon 2 other serversreads or searches
“Server identity, catalog digest, and tool availability”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
verify_evidence_bundleon 1 other serverreads or searches
“Verify a bundle's digest and re-hash its subjects”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- bundleobjectrequired

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 25 tools
Says what it returns: 100% of 25 tools
States limits, defaults or errors: 0% of 22 tools
Says when to use it: 0% of 25 tools
Items covered per tool: 2.1 of 4 on average

Counted from the listing

Parameters with a description: 73% of 40
Tools with a description: 100% of 25
Typical description length: 76 characters

The tool set

Counted from the listing

Tools: 25
Size of the list: about 2,628 tokens for an agent to load (characters ÷ 4)
Naming: 25 of 25 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 25 of 25 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

No config: the MCP bundle is a file to install in a client that supports bundles, not a command.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Published package can be started	Started and answered	matches	our test · 2026-10-23
Repository github.com/qompassai/fathom	Opens publicly	matches	api.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: ai.qompass · 7 servers
GitHub owner: an organization (qompassai)

Repository: github.com/qompassai/fathom
Stars: 0
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-22; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

4 of 5 record checks met · 4 do not apply

Not ranked by downloads: not an npm or PyPI package
Not ranked by stars: 0 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
Does not applyPackage names its licence with a standard (SPDX) identifierNot an npm or PyPI package.
Does not applyThe version the registry lists can be installed and is not withdrawnNot an npm or PyPI package.
Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
Does not applyNo known critical or high advisory in the package or its dependenciesNot an npm or PyPI package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about ai.qompass/fathom

Answered from the data above

Is ai.qompass/fathom safe to install?

We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. 4 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Has ai.qompass/fathom been security tested?

Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can ai.qompass/fathom do?

It lists 25 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, run code or commands and control a browser or desktop. We did not call any tool, so this describes the text, not the behaviour.

Can ai.qompass/fathom change or delete data?

4 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does ai.qompass/fathom publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Where is the source code of ai.qompass/fathom?

In github.com/qompassai/fathom, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

io.github.cameroncooke/XcodeBuildMCPalso has tools that controls a browser or desktop, creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.callstack/agent-deviceagent-devicealso has tools that controls a browser or desktop, creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.A9T9/uivision-mcpUi.Vision MCPalso has tools that controls a browser or desktop, creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.Buoy-gg/mcpalso has tools that controls a browser or desktop, creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.jumodada/drissionpage-mcpDrissionPage MCPalso has tools that controls a browser or desktop, creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.tugcantopaloglu/godot-mcpGodot MCPalso has tools that controls a browser or desktop, creates or changes data, runs code or commands, reads or searchescompare with this one

Active servers whose topic is also “developer-tools” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not applicable
Consent handling: not applicable
Sign-in metadata: not applicable

2 exercised10 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against

Does not apply to this server · 6

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted the published package in an isolated sandbox (read-only mode)
16 msConnected after 0 redirects.
Read the inventory: 25 tools, 0 resources, 0 prompts.
2,484 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

developer-tools

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

The pages we read do not state how the product is priced.

Programming language

Rust

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

standard input/output

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

mcpb

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Integrity hash

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Signature / provenance

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Dependency advisories

not checked

only npm and PyPI packages are audited

Popularity

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Publisher signals

owner: an organization · repository age: 0–30 days · stars: 0–9

api.github.com · 2026-10-22

Maintenance

active

api.github.com · 2026-10-22

Environment

your machine

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “ai.qompass/fathom: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.qompass/fathom

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/ai.qompass/fathom)](https://protocolprobe.com/mcp/servers/ai.qompass/fathom)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology