MCP server · Audited from source
headroom-ai MCP server
by headroomlabs-ai/headroomApache-2.0 licenceAudited 13 Nov 2026 · source 25b1342e6242
Is it safe? No — BLOCK, grade F (37/100). It exposes 3 tools: 2 read, 1 write and 0 destructive. The audit recorded 98 findings (4 critical, 0 high, 15 medium, 74 low). Maintainer's description: Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Cite
Cite this page
ModelsAtlas. “headroom-ai MCP server (headroomlabs-ai/headroom)”. Retrieved 13 Nov 2026. https://modelsatlas.com/mcp/headroomlabs-ai/headroom
Why this is BLOCK. The audit found 4 critical and 0 high findings; the most severe is Hard-coded secrets at .gitguardian.yaml:34. Each finding is listed below with its file and line.
Why this page is still public. People search for this server by name. Hiding it would leave them with the README's word alone; here they see what the code does. We list it so you can decide, and we do not show connect commands for BLOCK servers.
Trust audit
Audit 0.4.1 · full source read 13 Nov 2026
98 findings, listed below with the file and line each was found on. Grade A needs a sandboxed behavioural run too; this audit read the source only.
What the source does
- FilesystemDeclared9 observations
- NetworkDeclared9 observations
- ShellDeclared6 observations
- DependenciesNot pinnedSome ranges float
- SecretsFoundSee the findings
Findings (98)
Sorted by severity · the 25 most severe of 98 are listed
CRITICALHard-coded secretssecret.anthropic · .gitguardian.yaml:34
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
CRITICALHard-coded secretssecret.anthropic · crates/headroom-core/benches/auth_mode.rs:41
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
CRITICALHard-coded secretssecret.anthropic · crates/headroom-core/benches/auth_mode.rs:62
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
CRITICALHard-coded secretssecret.anthropic · crates/headroom-proxy/src/cache_stabilization/drift_detector.rs:761
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMCode injectioncode.dynamic_import · headroom/learn/registry.py:32
mod = importlib.import_module(f"headroom.learn.plugins.{mod_name}")- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · deploy/beacon/test-rollup.mjs:65
const beacon = (install, id, seq) =>
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · deploy/beacon/test-rollup.mjs:96
[`sessions/${PART}/a.json`]: [beacon('i1', 's1', 3), beacon('i1', 's2', 1)].join('\n'),- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · deploy/beacon/test-rollup.mjs:97
[`sessions/${PART}/b.json`]: beacon('i1', 's1', 9),- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · deploy/beacon/test-rollup.mjs:98
[`sessions/${PART}/c.json`]: beacon('i1', 's1', 7),- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.beacon_words · deploy/beacon/test-rollup.mjs:100
[`sessions/${PART}/d.json`]: beacon('i2', 's1', 2),- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.raw_ip · Dockerfile:212
CMD curl --fail --silent "http://127.0.0.1:${HEADROOM_PORT:-8787}/readyz"- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMNetwork egressnet.raw_ip · Dockerfile:255
CMD ["python3", "-c", "import os, urllib.request; urllib.request.urlopen('http://127.0.0.1:' + (os.environ.get('HEADROOM_PORT') or '8787') + '/readyz', timeout=5)"]- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMObfuscation / stealthobf.homoglyph · scripts/export_kompress_v2_onnx.py:243
"Verify: max|Δscore|=%.4f keep-decision agreement=%.1f%% (fp32 ~100%%, int8 ~98-100%%)",
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.anthropic · crates/headroom-core/tests/auth_mode.rs:172
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · docs/scripts/verify-sdk-wire.mjs:40
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · tests/test_compression/test_masks.py:247
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · tests/test_compression/test_masks.py:254
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · tests/test_compression/test_universal.py:354
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · tests/test_compression_safety_rails.py:375
Excerpt withheld: it is a secret, and we never print one.
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWCode injectioncode.deserialize · tests/test_pipeline_outcome_stage.py:129
restored = pickle.loads(pickle.dumps(snap))
- Why
- deserialises untrusted bytes into live objects
- Fix
- use json or yaml.safe_load
Tools it exposes
3 declared in source · 0 destructive
| Tool | What it does | Risk |
|---|---|---|
headroom | Show what Headroom snipped from each request (add | write |
headroom_retrieve | Retrieve original uncompressed content from Headroom | read |
lookup | Local fixture. | read |
Safer alternatives
jjjorfi/gfc
git-for-context — LLM context dedup: unchanged file re-reads collapse to hash-verified stubs, changed files return diffs. OpenCode plugin + zero-dep MCP server. Measured −34% per-turn context.
pcircle-ai/toonify-mcp
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
codefromkarl/contextatlas
ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector search, FTS5 and token-aware context packing.
Audit history
- ✕BLOCK F 37 / 100
First audit ·
25b1342e6242
README badge
Badges show the current verdict, BLOCK included
A badge cannot be hidden by the maintainer while the verdict is BLOCK. Fix the findings, push, and the re-audit updates it.
Questions about headroom-ai MCP server
What is the headroom-ai MCP server?
What tools does headroom-ai expose?
Is headroom-ai safe to connect to an agent?
What credentials does headroom-ai need?
How does headroom-ai run?
How current is this page?
I already installed headroom-ai. What should I do?
Can the verdict change?
Sources
- headroomlabs-ai/headroom on GitHub — the source we read, its licence, stars and activityObserved · 13 Nov 2026
- ModelsAtlas trust audit — BLOCK verdict for commit 25b1342e6242Observed · 13 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What is the headroom-ai MCP server?
- What tools does headroom-ai expose?
- Is headroom-ai safe to connect to an agent?