Atlas / MCP servers / rm-rf-prod / GroundTruth-MCP

GroundTruth-MCPBLOCK

mcp/rm-rf-prod/groundtruth-mcp

Self-hosted MCP server for live documentation, code audits, and best practices. 793+ curated libraries, 107 audit patterns, no rate limits.

Verdict
BLOCK
Grade
F
Trust score
52 /100
Exposed tools
33 33r · 0w · 0d
Transport
stdio · streamable-http
License
NOASSERTION
Stars
6
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Current, official documentation for coding agents, fetched when they ask.

GroundTruth is a self-hosted MCP server and command-line tool. Models write code from what they were trained on, so they still wrap components in forwardRef after React 19 made ref a regular prop, call cookies() synchronously after Next.js made it async, and emit @tailwind directives that Tailwind v4 replaced with @import "tailwindcss". GroundTruth gives the agent the library's own documentation at request time: it reads llms.txt, the docs site as markdown, or the GitHub repository, ranks the sections that answer the question, and checks that the answer covers the topic before returning it. It also audits your source with 107+ patterns and links every finding to the current fix. It runs on your machine. No account,

Read from source at commit cfbc88cbf344OBSERVED · 2026-10-10
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (npm)
claude mcp add gt-mcp --env GT_GITHUB_TOKEN=${GT_GITHUB_TOKEN} -- npx -y @groundtruth-mcp/[email protected]
03

Exposed tools (33)

33 read · 0 write · 0 destructive.

ToolRiskDescription
HighLibreadbuilding user interfaces rocks
LowLibreadunrelated
Next.jsreadThe React Framework for the Web
ReactreadA JavaScript library for building user interfaces
cached-pkgreadCached
cap-test-small-bodyreadA small package body streamed through a real ReadableStream, long enough to clear the 50-char tryFetch threshold.
corrupt-mem-pkgreadFreshly fetched package data replacing the corrupt memory cache entry, long enough to clear thresholds.
disk-pkgreadFrom disk
error-probe-pkgreadtest
evil-pkgreadA tiny helper.
gt_auditread
gt_auto_scanread
gt_batch_resolveread
gt_best_practicesread
gt_changelogread
gt_compareread
gt_compatread
gt_dispatchread
gt_examplesread
gt_get_docsread
gt_migrationread
gt_resolve_libraryread
gt_searchread
gt_snippetsread
my-packagereadA test package for the npm registry with enough content to exceed the 100 character minimum threshold
npm-score-pkgreadx
ok-pkgreadFast, tiny state manager.
rayonreadParallelism
reqwestreadHTTP client
serdereadA serialization framework for Rust
some-npm-pkgreadAn npm package
string-repo-pkgreadtest
tokioreadAsync runtime
04

Trust audit

BLOCKgrade F · trust 52/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (5 observation(s))
Network
declared (10 observation(s))
Shell
declared (11 observation(s))
Dependencies
not all pinned
Secrets in source
found

Findings (25)

HIGHCode injection · code.deserialize · CWE-78, CWE-94, CWE-95
src/sources/audit-patterns.ts:899
title: "pickle.loads() from untrusted source",
Why it matters. deserialises untrusted bytes into live objects
Fix. use json or yaml.safe_load
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/sources/audit-patterns.ts:855
title: "eval() or exec() with dynamic input",
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/sources/audit-patterns.ts:857
"`eval()` and `exec()` execute arbitrary Python code. If the argument is derived from user input or an external source, an attacker can run any code on the server.",
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/sources/audit-patterns.ts:858
fix: "Never pass user-controlled data to `eval()` or `exec()`. Use `ast.literal_eval()` for safe parsing of Python literals.",
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHNetwork egress · net.tls_off · CWE-200, CWE-319
src/sources/audit-patterns.ts:923
title: "requests with verify=False — TLS validation disabled",
Why it matters. certificate verification is disabled
Fix. leave verification on
HIGHNetwork egress · net.tls_off · CWE-200, CWE-319
src/sources/audit-patterns.ts:925
"Setting `verify=False` disables TLS certificate verification, making the connection vulnerable to man-in-the-middle attacks. An attacker can intercept and modify traffic.",
Why it matters. certificate verification is disabled
Fix. leave verification on
HIGHNetwork egress · net.tls_off · CWE-200, CWE-319
src/sources/audit-patterns.ts:926
fix: "Remove `verify=False`. If using a self-signed certificate, pass the CA bundle path: `verify='/path/to/ca-bundle.crt'`.",
Why it matters. certificate verification is disabled
Fix. leave verification on
HIGHNetwork egress · net.tls_off · CWE-200, CWE-319
src/sources/audit-patterns.ts:927
docsQuery: "Python requests verify=False TLS SSL certificate security",
Why it matters. certificate verification is disabled
Fix. leave verification on
MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319
src/constants.ts:90
/!\[.*?\]\(https?:\/\/[^)]*(?:exfil|steal|leak|callback|webhook|requestbin|hookbin|burp|interact\.sh|oast\.(?:me|site|fun|live|pro)|canarytokens|pipedream\.net|ngrok(?:\.io|-free\.app)|webhook\.site|b
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
Dockerfile:30
HEALTHCHECK CMD wget -qO- --header="Authorization: Bearer ${GT_AUTH_TOKEN}" "http://127.0.0.1:${GT_HTTP_PORT}/health" || exit 1
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
src/tools/audit-security-audit-patterns.test.ts:30
const matches = testLine("security", `const apiKey = "abcdefghijklmnopqrstuvwxyz1234";`);
LOWInventory / provenance · inv.hidden_file · CWE-1104
.node-version
.node-version
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWCode injection · code.deserialize · CWE-78, CWE-94, CWE-95
src/tools/audit-python-audit-patterns.test.ts:108
describe("pickle.loads()", () => {
Why it matters. deserialises untrusted bytes into live objects
Fix. use json or yaml.safe_load
LOWCode injection · code.deserialize · CWE-78, CWE-94, CWE-95
src/tools/audit-python-audit-patterns.test.ts:109
it("flags pickle.loads()", () => {
Why it matters. deserialises untrusted bytes into live objects
Fix. use json or yaml.safe_load
LOWCode injection · code.deserialize · CWE-78, CWE-94, CWE-95
src/tools/audit-python-audit-patterns.test.ts:110
expect(matchesPattern("pickle.loads() from untrusted source", `data = pickle.loads(raw_bytes)`)).toBe(true);
Why it matters. deserialises untrusted bytes into live objects
Fix. use json or yaml.safe_load
LOWCode injection · code.deserialize · CWE-78, CWE-94, CWE-95
src/tools/audit-python-audit-patterns.test.ts:113
it("flags pickle.load()", () => {
Why it matters. deserialises untrusted bytes into live objects
Fix. use json or yaml.safe_load
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/tools/audit-python-audit-patterns.test.ts:47
describe("eval() / exec()", () => {
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/tools/audit-python-audit-patterns.test.ts:48
it("flags eval()", () => {
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/tools/audit-python-audit-patterns.test.ts:119
it("flags hashlib.md5()", () => {
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/tools/audit-python-audit-patterns.test.ts:122
`hashed = hashlib.md5(password.encode()).hexdigest()`,
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/tools/audit-python-audit-patterns.test.ts:126
it("flags hashlib.sha1()", () => {
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
src/tools/audit-python-audit-patterns.test.ts:129
`h = hashlib.sha1(data)`,
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/services/best-practices/discovery.ts:2
import { extractRelevantContent, tokenize } from "../../utils/extract.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/services/best-practices/discovery.ts:3
import { sanitizeContent } from "../../utils/sanitize.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/services/best-practices/escalate.ts:3
import { extractRelevantContent } from "../../utils/extract.js";

Gates applied: no_behavioural_pass.

Audited 2026-10-10 · audit v0.4.1 · source sha cfbc88cbf344full audit observations/trust-audit/mcp-server/rm-rf-prod__groundtruth-mcp.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-10cfbc88cbf344BLOCKF52first audit
06

Questions

What is the GroundTruth-MCP MCP server?

Self-hosted MCP server for live documentation, code audits, and best practices. 793+ curated libraries, 107 audit patterns, no rate limits.

What tools does GroundTruth-MCP expose?

33 in total: 33 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is GroundTruth-MCP safe to connect to an agent?

No — not without reading the findings first. The audit graded it F (52/100) and found 8 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What credentials does GroundTruth-MCP need?

It reads GT_AUTH_TOKEN, GT_GITHUB_TOKEN and GT_JINA_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does GroundTruth-MCP run?

It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @groundtruth-mcp/gt-mcp at 8.0.1.

How current is this page?

The grade is for one exact copy of the source (cfbc88cbf344), read on 2026-10-10. The repository is watched and re-audited when it changes.

Advertisement