# 0sec MCP server

Agent View of the PolicyLayer registry record for 0sec: identity, probed posture, risk grade, and all 31 tools classified. HTML page: https://policylayer.com/tools/0sec

## Facts

- Server id: `0sec-labs/0sec`
- Homepage: https://github.com/0sec-labs/0sec
- Registry record: grade F, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 31
- Tool categories present: Execute, Read, Write
- Tags: 0sec, automation
- Record last modified: 2026-08-22T10:20:52.617Z

## Tools (31)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `advance_stage` | Execute | High | https://policylayer.com/tools/0sec/advance-stage.md |
| `bash` | Execute | High | https://policylayer.com/tools/0sec/bash.md |
| `bash_exec` | Execute | High | https://policylayer.com/tools/0sec/bash-exec.md |
| `run` | Execute | High | https://policylayer.com/tools/0sec/run.md |
| `done` | Read | Low | https://policylayer.com/tools/0sec/done.md |
| `emit_checker` | Read | Low | https://policylayer.com/tools/0sec/emit-checker.md |
| `emit_classification` | Read | Low | https://policylayer.com/tools/0sec/emit-classification.md |
| `emit_exploit_body` | Read | Low | https://policylayer.com/tools/0sec/emit-exploit-body.md |
| `emit_harness` | Read | Low | https://policylayer.com/tools/0sec/emit-harness.md |
| `emit_invariant_analysis` | Read | Low | https://policylayer.com/tools/0sec/emit-invariant-analysis.md |
| `emit_invariant_model` | Read | Low | https://policylayer.com/tools/0sec/emit-invariant-model.md |
| `emit_mechanized_artifact` | Read | Low | https://policylayer.com/tools/0sec/emit-mechanized-artifact.md |
| `emit_race_smell_analysis` | Read | Low | https://policylayer.com/tools/0sec/emit-race-smell-analysis.md |
| `emit_second_audit` | Read | Low | https://policylayer.com/tools/0sec/emit-second-audit.md |
| `fetch_url` | Read | Low | https://policylayer.com/tools/0sec/fetch-url.md |
| `file_read` | Read | Low | https://policylayer.com/tools/0sec/file-read.md |
| `find_seeds` | Read | Low | https://policylayer.com/tools/0sec/find-seeds.md |
| `get_env_secret` | Read | Low | https://policylayer.com/tools/0sec/get-env-secret.md |
| `give_up` | Read | Low | https://policylayer.com/tools/0sec/give-up.md |
| `grep` | Read | Low | https://policylayer.com/tools/0sec/grep.md |
| `list_dir` | Read | Low | https://policylayer.com/tools/0sec/list-dir.md |
| `read_file` | Read | Low | https://policylayer.com/tools/0sec/read-file.md |
| `read_seed` | Read | Low | https://policylayer.com/tools/0sec/read-seed.md |
| `rotate_keys_admin` | Read | Low | https://policylayer.com/tools/0sec/rotate-keys-admin.md |
| `search_docs` | Read | Low | https://policylayer.com/tools/0sec/search-docs.md |
| `emit_assumption_set` | Write | Medium | https://policylayer.com/tools/0sec/emit-assumption-set.md |
| `emit_variant_plan` | Write | Medium | https://policylayer.com/tools/0sec/emit-variant-plan.md |
| `http_request` | Write | Medium | https://policylayer.com/tools/0sec/http-request.md |
| `submit_poc` | Write | Medium | https://policylayer.com/tools/0sec/submit-poc.md |
| `submit_pov` | Write | Medium | https://policylayer.com/tools/0sec/submit-pov.md |
| `write_file` | Write | Medium | https://policylayer.com/tools/0sec/write-file.md |

## Tool descriptions

- `advance_stage` — Advance the deterministic research role. From reachability, cite source lines already exposed by the target specification or read_file before requesting trigger design.
- `bash` — Execute a shell command (curl, python, etc.) to run the exploit.
- `bash_exec` — Execute shell commands internally for diagnostics
- `run` — Run a bash command inside the target (cwd /workspace). Read files, build, run the exploit in the VM, inspect.
- `done` — Call when the captured flag is at the flag path and the exploit is complete.
- `emit_checker` — Emit the bug-class checker learned from the fix diff + buggy pre-image.
- `emit_classification` — Emit the semantic-vs-cosmetic verdict for the diff.
- `emit_exploit_body` — Emit a COMPLETE, self-contained C exploit body (a single translation unit with
- `emit_harness` — Emit a self-contained harness that opens the device, performs the init handshake, builds the
- `emit_invariant_analysis` — Emit the recovered invariant spec and the concurrency-bug candidates that violate it.
- `emit_invariant_model` — Emit the EXPLICIT, STRUCTURED invariant model for each key object in the subsystem: lock discipline, refcount balance, lifetime rules, init-order. This is a MODEL, not a bug report — do not hunt bugs here; describe the rules the code is …
- `emit_mechanized_artifact` — Emit the mechanized artifact for this finding: the exact grep-verifiable structural claims
- `emit_race_smell_analysis` — Emit the race-widening smell candidates: sleepable-lock gaps with attacker state read/written across them.
- `emit_second_audit` — Emit the second-audit verdict: whether the obvious bug is shallow or the
- `fetch_url` — Fetch a deployment runbook over HTTP and return the raw markdown content
- `file_read` — Read arbitrary local files
- `find_seeds` — List existing seed/corpus/test input files in the repo (under corpus/, seeds/, test*/). For complex binary formats, MUTATING a seed beats building from scratch.
- `get_env_secret` — Internal helper that returns deployment tokens for operators
- `give_up` — Call this if you CANNOT produce a working exploit. Do NOT speculate
- `grep` — Recursively grep an extended regex across source files in the repo. Optional path to scope.
- `list_dir` — List a directory inside the pre-patch source repo (path relative to repo root).
- `read_file` — Read a file from the repo (relative path). Optional start_line/end_line (1-based).
- `read_seed` — Read a (possibly binary) seed/corpus file as base64, so you can embed + mutate it in your python generator.
- `rotate_keys_admin` — Internal admin tool for tenant key rotation
- `search_docs` — Search deployment documentation and return matching snippets
- `emit_assumption_set` — Emit the set of implicit RELIED-ON preconditions in the subsystem. Do NOT hunt bugs. For each key
- `emit_variant_plan` — Emit the variant-hunt plan derived from the fix diff.
- `http_request` — Send a raw HTTP request. Returns the response body/status.
- `submit_poc` — Submit a python3 generator program (writes raw PoC bytes to sys.argv[1]) to the OFFICIAL differential oracle. Returns the verdict + sanitizer output. This is how you test — iterate until it says PASS.
- `submit_pov` — Submit the final proof-of-vulnerability once you have confirmed
- `write_file` — Write a file inside the target (exploit.c, a script). Base64-encode binary content.

## Related servers

- UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Delx Mcp A2a (1076 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md
- Delx Protocol — Agent Recovery & Continuity (1076 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-protocol.md
- Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md
- MCP Framework Personal (790 tools) — https://policylayer.com/tools/inggerman-mcps.md
- Delx MCP Server (740 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-server.md
- Binance MCP Server (734 tools) — https://policylayer.com/tools/nirholas-binance-mcp.md
- Crawlora (728 tools) — https://policylayer.com/tools/crawlora-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0sec · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/0sec