# Fathom (mcpb · linux-x64)

Reverse-engineering tools for agents over MCP/A2A, with evidence-carrying findings.

- Trust score: 38/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- mcpb · `linux-x64`: 38/100 (this document), [markdown](https://verifymcp.io/servers/ai-qompass-fathom/fathom-mcp-linux-x64.md), [page](https://verifymcp.io/servers/ai-qompass-fathom/fathom-mcp-linux-x64)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/qompassai/fathom/releases/download/v0.1.1/fathom-mcp-0.1.1-linux-x64.mcpb`
- Transport: `stdio`
- SHA-256: `31e6127f1c9fdeccf43bb95073e201ecc6f6959caab64c05a7ba915f5e8bbe19`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1115 tokens (~44/item across 25 items; 25 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 73% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 25 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Fathom MCP server?

Fathom ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 31e6127f1c9fdeccf43bb95073e201ecc6f6959caab64c05a7ba915f5e8bbe19; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/qompassai/fathom/releases/download/v0.1.1/fathom-mcp-0.1.1-linux-x64.mcpb`
- SHA-256: `31e6127f1c9fdeccf43bb95073e201ecc6f6959caab64c05a7ba915f5e8bbe19`

### Verify on macOS / Linux

```bash
echo "31e6127f1c9fdeccf43bb95073e201ecc6f6959caab64c05a7ba915f5e8bbe19  fathom-mcp-0.1.1-linux-x64.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\fathom-mcp-0.1.1-linux-x64.mcpb).Hash -eq "31e6127f1c9fdeccf43bb95073e201ecc6f6959caab64c05a7ba915f5e8bbe19"
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 38, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 37, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 36, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-19 (score 35)

First indexed and scored.

## MCP tools (25)

### `analyze_art_style` (~63 tokens)

Measured style spec of an image or GIF: palette, grade statistics, shading model, animation timing grammar, sheet geometry

Input parameters:

- `palette_colors` (integer): Palette clusters to extract (default 8)
- `target` (string, required): Path under a configured target root

### `analyze_function` (~36 tokens)

Function dossier: listing, bounded decompile, callers, callees

Input parameters:

- `function` (string, required)
- `target` (string, required)

### `analyze_javascript_application` (~39 tokens)

Static analysis of a JS/Electron application: modules, graph, IPC boundaries

Input parameters:

- `target` (string, required): Path under a configured target root

### `apply_style_via_lumen` (~137 tokens)

Grade an image with lumen's style engine (stdio MCP style_apply) and verify the output against an optional reference style spec

Input parameters:

- `lumen_program` (string, required): Lumen binary name; must be in allow_programs
- `output` (string, required): Output file name (.png), written under the state dir
- `preset` (string, required): Lumen style preset name (see lumen style_list)
- `reference` (string): Optional art target whose style spec the output is verified against
- `strength` (number): Grade strength (default 1.0)
- `target` (string, required): Path under a configured target root

### `binary_overview` (~32 tokens)

Program identity, memory map, and inventory counts

Input parameters:

- `target` (string, required): Path under a configured target root

### `capture_process` (~44 tokens)

Run an allowlisted command confined, capturing output, exit, timing, and hashes

Input parameters:

- `command` (array, required): argv; the program must be allowlisted by name in config

### `compare_artifacts` (~35 tokens)

Compare two artifacts: identity, sizes, and byte equality

Input parameters:

- `a` (string, required)
- `b` (string, required)

### `export_evidence_bundle` (~27 tokens)

Package evidence envelopes into a digest-sealed bundle

Input parameters:

- `results` (array, required)

### `inspect_android_apk` (~46 tokens)

Static APK inventory: ZIP contents, contents classes, and the binary-XML manifest (package, permissions, components)

Input parameters:

- `target` (string, required): Path under a configured target root

### `inspect_artifact` (~33 tokens)

File identity and classification, or a bounded directory inventory

Input parameters:

- `target` (string, required): Path under a configured target root

### `inspect_asar` (~37 tokens)

ASAR archive inventory: entries, sizes, offsets, unpacked flags

Input parameters:

- `target` (string, required): Path under a configured target root

### `inspect_binary_layout` (~34 tokens)

Container layout and mitigation candidates, read directly (no engine)

Input parameters:

- `target` (string, required): Path under a configured target root

### `inspect_evm_bytecode` (~55 tokens)

Offline EVM bytecode: dispatcher scan and inferred function selectors

Input parameters:

- `bytecode` (string): Hex bytecode, optional 0x prefix
- `target` (string): Or a file under a target root

### `inspect_firmware` (~42 tokens)

Firmware inspection: header/format detection, embedded-filesystem signature scan, entropy profile (no extraction)

Input parameters:

- `target` (string, required): Path under a configured target root

### `inspect_managed_assembly` (~43 tokens)

.NET metadata inventory: identity, types, methods, P/Invoke, signature digests

Input parameters:

- `target` (string, required): Path under a configured target root

### `inspect_source_map` (~64 tokens)

Source-map v3 parsing: sources, sourcesContent presence, segments, and generated-to-original position mapping

Input parameters:

- `generated_column` (integer)
- `generated_line` (integer)
- `target` (string, required): Path to a .map file under a configured target root

### `inspect_web_capture` (~34 tokens)

HAR capture reading: request/response inventory and payload exposure

Input parameters:

- `target` (string, required): Path under a configured target root

### `list_functions` (~28 tokens)

Function inventory with classifications and signatures

Input parameters:

- `target` (string, required): Path under a configured target root

### `list_names` (~30 tokens)

Symbol inventory: addresses, names, types

Input parameters:

- `target` (string, required): Path under a configured target root

### `list_strings` (~27 tokens)

Defined-string inventory with addresses

Input parameters:

- `target` (string, required): Path under a configured target root

### `observe_browser` (~37 tokens)

Chromium-headless page observation: title, meta, script, link, and form inventory from the serialized DOM

Input parameters:

- `url` (string, required)

### `remap_palette` (~112 tokens)

Native deterministic palette remap of an image (nearest or exact) to a supplied palette or another asset's measured palette

Input parameters:

- `mode` (string): Default nearest
- `output` (string, required): Output file name (.png), written under the state dir
- `palette` (array): #RRGGBB entries (1..=256); mutually exclusive with palette_from
- `palette_from` (string): Art target whose measured palette to use
- `target` (string, required): Path under a configured target root

### `search_inventory` (~33 tokens)

Substring search across functions, symbols, and strings

Input parameters:

- `query` (string, required)
- `target` (string, required)

### `session_info` (~18 tokens)

Server identity, catalog digest, and tool availability

### `verify_evidence_bundle` (~29 tokens)

Verify a bundle's digest and re-hash its subjects

Input parameters:

- `bundle` (object, required)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/ai-qompass-fathom/fathom-mcp-linux-x64#diagnostics

## Score history

- 2026-10-24: 38
- 2026-10-23: 37
- 2026-10-22: 37
- 2026-10-21: 36
- 2026-10-20: 36
- 2026-10-19: 35

## Common questions

### What is the Fathom MCP server?

Fathom is an MCP server listed in the public MCP registry as ai.qompass/fathom. Reverse-engineering tools for agents over MCP/A2A, with evidence-carrying findings. This page covers its MCPB bundle (https://github.com/qompassai/fathom/releases/download/v0.1.1/fathom-mcp-0.1.1-linux-x64.mcpb).

### Is the Fathom MCP server safe to use?

Fathom scores 38 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Fathom MCP server expose?

Fathom exposes 25 tools: analyze_art_style, analyze_function, analyze_javascript_application, apply_style_via_lumen, binary_overview, and 20 more. Their descriptions and schemas cost roughly 1,115 tokens of context every time the server is loaded.

### What licence is the Fathom MCP server under?

Fathom declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/qompassai/fathom
- Website: https://qompass.ai/solutions/fathom/
- Changelog RSS feed: https://verifymcp.io/servers/ai-qompass-fathom/fathom-mcp-linux-x64.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-qompass-fathom/fathom-mcp-linux-x64.json
- HTML version of this page: https://verifymcp.io/servers/ai-qompass-fathom/fathom-mcp-linux-x64