seam-mcp@0.2.1
CAUTION· static onlyPublisher claims: "Local code intelligence MCP server for AI agents" Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Before you give it your token
- It will ask for
SEAM_LLM_API_KEYConfiguration, not credentials: SEAM_AFFECTED_DEPTH, SEAM_BUILTIN_FILTERING, SEAM_CLUSTER_MIN_SIZE, SEAM_CLUSTER_NAMING, SEAM_DB_PATH, SEAM_DEBOUNCE_MS, SEAM_EMBED_MODEL, SEAM_FLOW_ENTRY_LIMIT, SEAM_FLOW_MAX_BREADTH, SEAM_FLOW_MAX_DEPTH, SEAM_FLOW_REACH_DEPTH, SEAM_FUZZY_MAX_CANDIDATES, SEAM_FUZZY_MAX_DIST, SEAM_IMPACT_MAX_RESULTS, SEAM_IMPORT_RESOLUTION, SEAM_LLM_MODEL, SEAM_LOG_LEVEL, SEAM_MAX_AFFECTED_FILES, SEAM_MAX_AFFECTED_SYMBOLS, SEAM_MAX_FILE_BYTES, SEAM_MAX_IMPACT_SYMBOLS, SEAM_MAX_IMPORT_CANDIDATES, SEAM_MAX_SIGNATURE_LEN, SEAM_PACK_MAX_COMMENTS, SEAM_PACK_NEIGHBOR_LIMIT, SEAM_PACK_PER_FILE_CAP, SEAM_PROXIMITY_MAX_CANDIDATES, SEAM_RRF_K, SEAM_SEMANTIC, SEAM_SEMANTIC_LIMIT, SEAM_SEMANTIC_SCAN_CAP- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- nothing has run yet
- What we could not test
- everything: the server has not run yet
Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-17 and scored it 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
watcher_proc = subprocess.Popen( # noqa: S603 — controlled internal command, no shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.npx gitnexus analyze --embeddingsFix: Pin versions and sources; vendor anything fetched at install time.…the point at which Seam can replace GitNexus for this repo's own "impact before edit / detect_changes before commit" workflow (`CLAUDE.md`). That's the concrete success signal for the slice. - **Confidence is the head…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx gitnexus analyze --embeddingsFix: Pin versions and sources; vendor anything fetched at install time.> If any GitNexus tool warns the index is stale, run `npx gitnexus analyze` in terminal first.Fix: Pin versions and sources; vendor anything fetched at install time.bad.write_bytes(b"\x00\x01\x02\x03\xff\xfe binary content")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.npx gitnexus analyzeFix: Pin versions and sources; vendor anything fetched at install time.npx gitnexus analyzeFix: Pin versions and sources; vendor anything fetched at install time.**Re-index:** run `npx gitnexus analyze` when `gitnexus status` shows stale.Fix: Pin versions and sources; vendor anything fetched at install time.> If any GitNexus tool warns the index is stale, run `npx gitnexus analyze` in terminal first.Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for seam-mcp@0.2.1 as of 21 min ago. This is the package itself, not its dependencies.
What would make this Verified
16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim catafal: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Hex-encoded string detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.