MCP Blast-Radius Auditor
Static blast-radius audit for MCP servers before agent install. Manifest optional.
Open source Open in the app JSON README (API)
About
Static blast-radius audit for MCP servers before agent install. Manifest optional.
Details
- Kind
- MCP servers
- Topic
- No topic detected
- Publisher
- aos-standard
- Origin
- official
- Category
- ferramentas
- Transport
- local
- Version
- 0.2.4
- Last push
- 2026-07-19T09:34:58Z
- Repository state
- ativo
- Language
- Python
- License
- MIT
- Added
- 2026-08-29 03:02:26
- Updated
- 2026-08-29 03:02:26
- Origin id
io.github.aos-standard/mcp-blast-radius
README
# MCP Blast-Radius Auditor <!-- mcp-name: io.github.aos-standard/mcp-blast-radius --> [](https://github.com/aos-standard/mcp-blast-radius/blob/main/BADGE_CRITERIA.md) > **See what any MCP server can actually touch — before you add it to your agent.** No manifest? You still get the full blast-radius report. Add a manifest to also catch divergences. > Also, if the server declares a manifest: **Catch an MCP server that touches files it said it wouldn't — and block the merge in CI.** Statically extract what a third-party MCP server can reach (files, network, subprocess, env) via surface-level analysis. Compare against declared boundaries when a manifest is present. **Scan scope (default):** production package only — excludes `tests/`, `docs/`, `examples/`, `scripts/`, `benchmarks/`, `.github/`, and `test_*.py` patterns; JSON output includes `scan_scope` and `excluded_file_count`. Pass `--include-peripheral` to scan the full repo. ## Try it in 3 steps **① Scan your server in one command** ```bash pip install mcp-blast-radius==0.2.5 mcp-blast-radius-gate --gate-mode advisory --target-dir /path/to/your-mcp-server ``` Point `--target-dir` at your shipping package root (e.g. `src/`). Default scope excludes tests, docs, and scripts. **② Read the JSON** | Field | What it means | |-------|----------------| | `gate_pass` | Scan finished (`advisory` = report either way; `blocking` = exit 1 on divergences) | | `blocking_reasons` | Lines starting with `DIVERGENCE:` = declared vs. observed mismatch (if you ship a manifest) | | `blast_radius` | Static capability surface (network, subprocess, env, filesystem) | | `confidence` labels | `declared` / `observed-static` / `cannot-determine` — static only, upper bounds | Undeclared capability is usually drift, not malice. Treat network/subprocess counts as **upper bounds**, not confirmed traffic. **③ Apply for an audit badge (optional, opt-in)** Ran a clean scan and want a signed README badge? [Open a badge application](https://github.com/aos-standard/mcp-blast-radius/issues/new?template=badge-application.yml) — paste your command and JSON. Free, 90-day attestation, no phone-home. Criteria: [BADGE_CRITERIA.md](BADGE_CRITERIA.md). To verify any published attestation independently: `pip install cryptography`, then run `packaging/scripts/verify_attestation.py` (accepts local paths or HTTPS URLs). See [BADGE_CRITERIA.md §Verify](BADGE_CRITERIA.md#verify-any-badge). --- ## Machine-readable metadata - **Agent Card** (capabilities, limitations, pricing): [agent_card.json](https://raw.githubusercontent.com/aos-standard/mcp-blast-radius/main/packaging/agent_card.json) - **Catalog entry** (pricing, install, MCP endpoint): [aos-standard/catalog](https://raw.githubusercontent.com/aos-standard/catalog/main/catalog.json) - **Spec**: [AOS-v0.1](https://github.com/aos-standard/AOS-spec) ## Example walkthrough ```bash git clone --depth 1 https://github.com/oraios/serena.git /tmp/serena mcp-blast-radius-gate --gate-mode advisory --target-dir /tmp/serena ``` Inspect `blast_radius` and any `DIVERGENCE:` lines in `blocking_reasons`. ## Report a scan question [Open a GitHub issue](https://github.com/aos-standard/mcp-blast-radius/issues/new) with your JSON output (structured template loads automatically). ## 30-second scan ```bash pip install mcp-blast-radius mcp-blast-radius-gate --gate-mode blocking --target-dir /path/to/mcp-server ``` `pipx run mcp-blast-radius` starts the **MCP stdio server** (for Claude Desktop / Cursor). For CLI scanning, use `mcp-blast-radius-gate` as above. - **Red (blocking):** divergence detected — code touches paths or capabilities not declared in manifest. - **Green:** no divergences (or no manifest — blast radius report only, advisory pass). ## Install ```bash python3 -m venv .venv source .venv/bin/activate pip install . ``` ## CLI entry ```bash mcp-blast-radius # MCP stdio server mcp-blast-radius-gate # CI gate (default blocking, exit 1 on fail) ``` ### CI blocking gate ```bash mcp-blast-radius-gate --gate-mode blocking --target-dir . # no divergences → exit 0 / divergences or declaration violations → exit 1 ``` ## MCP tools - `aos_compliance_validate` — scan one MCP server directory (`target_dir` required; `tool_id` optional label) - `aos_compliance_self_test` — wiring smoke test Default `gate_mode=advisory`. Use `gate_mode=blocking` in CI to fail on divergences. ## What is extracted | Layer | Scope | Confidence | |-------|-------|------------| | Dependencies | `requirements.txt`, `pyproject.toml`, `package.json` | `declared` | | Python AST | imports, file I/O, network, env, subprocess; MCP tool attribution | `observed-static` / `cannot-determine` | | Divergence | manifest `permitted_output_paths` / `oracle_paths` vs observed access | blocking when mismatch | **Limitations:** Static analysis only. Dynamic imports, `getattr`/`eval`, obfuscation, and native extensions may hide capabilities. We do not claim complete coverage — every finding includes a `confidence` label. ## Environment | Variable | Purpose | |----------|---------| | `AOS_VALIDATOR_TARGET_DIR` | Default scan root when `target_dir` is omitted | | `AOS_VALIDATOR_MCP_LOG` | JSONL path for local tool call log (never sent externally) | | `AOS_VALIDATOR_CALLER` | Caller label (`ci`, `smoke_self_call`, etc.) | ## Example ```bash aos_compliance_validate target_dir=/path/to/my-mcp-server gate_mode=blocking ``` ## License MIT