CodeNibBLOCK
Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Find the right code. Trace the calls. Give Claude Code and Codex source context and typed graph navigation across languages.
71.4% code-block Recall@5 on 100 real issues. Model-planned grep → Jev: +12.8 percentage points over the same grep candidates without reranking. Experimental result · Method and limitations
Use with your agent · Browse a Wiki · Languages · Reproductions · Releases
64ad85239484OBSERVED · 2026-10-07Connect
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 mcp add codenib -- uvx codenib==0.2.4 mcp
Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
explore_context | read | return query |
probe | read | return payload |
search_context | read | return query |
Trust audit
BLOCKgrade F · trust 40/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (9 observation(s))
- Network
- declared (7 observation(s))
- Shell
- declared (10 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
store._store = pickle.load(f)
cache._cache = pickle.load(f)
payload = pickle.load(handle)
loaded = yaml.load(handle, Loader=_UniqueKeySafeLoader) or {}g = pickle.load(f)
echo "Running SWE-bench Lite dev rerank eval (filter: ${FILTER_INSTANCE})"echo "Running SWE-bench Lite dev rerank eval (filter: ${FILTER_INSTANCE})"echo "Running SWE-bench Lite dev retrieval eval (filter: ${FILTER_INSTANCE})""html": "<span class=\"hljs-keyword\">def</span> <span class=\"hljs-title function_\">rebuild_auth</span>(<span class=\"hljs-params\">\n self, prepared_request: PreparedRequest, response: Response\
"content": " headers = prepared_request.headers\n original_url = original_request.url\n url = prepared_request.url\n\n if \"Authorization\" in headers and self.should_strip
codegraph-claude.webm
module = importlib.import_module(module_path)
params["callback_url"] = callback
f" Δtoken (compact−grep): {m:+.0f} [{lo:+.0f},{hi:+.0f}]{_sig(lo,hi)}"f" Δtoken (compact−{bn}): {st.fmean(tok):+.0f} [{lo:+.0f},{hi:+.0f}]{_sig(lo,hi)}""Δrec@5",
"Δcost%",
"Δturns",
api_key="offline-audit-fixture",
GrepJevConfig(api_key="install-smoke-fixture"),
secret = "boundary-spanning-secret"
secret = "decoded-runtime-secret"
secret = "configured-secret-value"
.clang-format
.flake8
Gates applied: no_behavioural_pass.
64ad85239484full audit observations/trust-audit/mcp-server/sysevol-ai__codenib.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 64ad85239484 | BLOCK | F | 40 | first audit |
Questions
What is the CodeNib MCP server?
Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.
What tools does CodeNib expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is CodeNib safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (40/100) and found 10 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 CodeNib need?
It reads ANTHROPIC_API_KEY, CODENIB_DEMO_API_KEY, CODENIB_DEMO_WIKI_API_KEY, CODENIB_EMBEDDING_API_KEY, CODENIB_EMBEDDING_API_KEY_ENV, CODENIB_WIKI_MEDIA_API_KEY, CODENIB_WIKI_VISUAL_FACTS_API_KEY, GOOGLE_APPLICATION_CREDENTIALS, OPENAI_API_KEY and OPENROUTER_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 CodeNib run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as codenib-qa-demo at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (64ad85239484), read on 2026-10-07. The repository is watched and re-audited when it changes.