emo-cyber-agent
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.

EMO-Cyber-Agent — the security subagent your AI stack can actually trust
Stop letting your coding agent guess about security. Give it a specialist: scoped read-only audits, evidence-backed findings, and verification plans — over CLI, MCP, or Python, with zero code changes and zero invented results.
✅ 2,738 tests green | Full suite passing, 36/36 schemas valid |
🔌 7 MCP tools | Works with OpenCode, Pi, Hermes, Jan, AnythingLLM |
🖥️ 3 OSs proven | Live runtime parity: Linux + Windows + macOS |
🔒 Read-only by design | Default-deny policy engine; it cannot edit your code |
Get value in 60 seconds
pip install emo-cyber # requires Python >= 3.11
cyber-agent audit . --format json > result.jsonThat's it — a machine-checkable security audit of your project. No API keys, no provider lock-in, no code changes. Then wire it into your agent:
{ "mcpServers": { "emo-cyber-agent": { "command": "cyber-agent", "args": ["mcp"] } } }⭐ If this saves you one bad merge, star the repo — it keeps the project alive.
Related MCP server: mcp-audit
Who it's for
AI agent builders — your Codex/Cline/OpenCode agent writes fast and breaks things fast. Delegate every security question to a governed specialist instead of a confident guess.
CI / platform teams — gate merges on stable JSON contracts and machine-readable exit codes, not on prose opinions.
Security reviewers — triage evidence-linked findings (with provenance and verification plans) instead of chasing hallucinations.
Why governed security for agents
AI coding agents ship code fast — and every generated diff, prompt, dependency, and tool call is a new attack surface. Generic assistants will happily opine about security, but their answers are ungrounded, unverifiable, and bound to no policy. EMO-Cyber-Agent exists for the gap in between: a specialist subagent that owns the security workflow, runs deterministic checks around probabilistic reasoning, and returns findings your pipeline can actually act on.
What it does
Scoped security audits of a project tree (
quick,standard,deep), with focus areas (auth,secrets,deps, …).Focused reviews of a target, verification planning for a candidate finding (plans, never exploits), and evidence-linked reports in JSON, JSONL, or Markdown.
Threat-intel lookups (leak monitor, feed triage, ATT&CK mapping — defensive knowledge only, no network calls, no execution) via MCP.
Stable JSON contracts across CLI, MCP, and the Python API, so results are machine-checkable in CI.
What it does not do
No auto-remediation and no production changes by default.
No exploit development and no offensive operations.
Not a replacement for SAST, SCA, secret scanners, DAST, runtime security, or human security review.
No scores-as-verdicts: findings carry evidence and provenance, not ratings.
EMO-Cyber vs the alternatives
Generic AI assistant | Traditional scanner | EMO-Cyber-Agent | |
Grounded in your repo | ❌ guesses | ✅ rules | ✅ evidence-linked |
Understands agent workflows | ❌ | ❌ | ✅ MCP-native, 7 tools |
Policy-enforced (not prompt-suggested) | ❌ | ✅ | ✅ default-deny engine |
Verification before confirmation | ❌ | ⚠️ partial | ✅ plans + provenance |
Model-agnostic, no lock-in | ❌ | ✅ | ✅ bring any model |
Read-only, cannot break prod | ❌ | ✅ | ✅ by design |
Why it is different
Model-agnostic. No weights, no provider lock-in. The product is the methodology, control loop, tool contracts, and evidence model — bring any model or run it model-free in CI.
Policy-enforced, not prompt-suggested. A default-deny
PolicyEnginein Core decides; CLI and MCP are thin adapters that cannot widen capabilities, whatever a prompt or tool description claims.Evidence-first. No material finding without evidence; tool outputs are data, never instructions; repository content is untrusted by default.
Verification before confirmation. Candidates become plans with methods, locators, and rationale — confirmation requires evidence.
Read-only by default. Destructive actions need an explicit permission transition; progress is advisory-only and recovery is bounded and fail-closed.
Architecture
Host / CI / You ──▶ CLI · MCP (stdio + Streamable HTTP) · Python API
│ thin adapters, no authority
▼
Core: Policy → Tools → Evidence → Reasoning
→ Verification → Findings → ReportingCore owns every security decision. Deterministic tool adapters (argv-only,
confined, secret-free execution) surround the reasoning loop; the evidence
graph correlates deterministically; the finding lifecycle gates promotion.
Details: docs/02-architecture.md, docs/03-security-methodology.md.
Quick start
pip install emo-cyber # requires Python >= 3.11
cyber-agent --help
cyber-agent doctor # presence checks; never prints secrets
cyber-agent audit . --format json > result.jsonFrom source (developers):
pip install -e '.[all]'Docker (reproducible runtime and test target):
make docker-build
make docker-run
make docker-test
make docker-unitThe runtime runs as an unprivileged user with a read-only filesystem, no
Linux capabilities, and no network access. See docs/docker.md for the
security model and release-image pinning requirements.
MCP and integrations
Register once as an MCP server, then delegate from any compatible host:
{ "mcpServers": { "emo-cyber-agent": { "command": "cyber-agent", "args": ["mcp"] } } }Seven tools (the last opt-in): cyber_audit, cyber_review,
cyber_verify, cyber_report, cyber_status, cyber_extensions,
cyber_threat_intel. Transports: stdio plus Streamable HTTP
(localhost by default, with Host/Origin/session validation).
Per-host guides: docs/integrations/ (OpenCode, Pi, Hermes, Jan,
AnythingLLM, generic MCP, delegation rules, security model).
Host | Status |
Generic MCP host (stdio) | Contract Tested |
OpenCode | Supported (config), Contract Tested discovery |
Pi (stdio / Streamable HTTP) | Supported (config), project-scoped |
Hermes (per-server filtering) | Supported (config), least-surface guidance |
Jan (Desktop + Agent/CLI shared config) | Supported (config) |
AnythingLLM (workspace/RAG = untrusted inputs) | Supported (config), boundary guidance |
Levels: Supported = config + mapping shipped; Contract Tested = in-repo
contract tests; Environment Tested = live binary exercised (where available);
otherwise Not Tested — see docs/integrations/ per host.
Example workflow: an authorized audit, end to end
# 1. Check operational presence (no secrets printed).
cyber-agent doctor
# 2. Run a scoped, read-only audit; findings never change the exit code.
cyber-agent audit ./my-service --mode standard --format json > audit.json
python -c "import json; print(json.load(open('audit.json'))['result']['status'])"
# 3. Request a verification plan for a candidate (input is never authorization).
cyber-agent verify --candidate cand.json --method static-review \
--kind sast --locator src/auth/login.py:42 --rationale "unverified input reaches query" \
--audit-id <id-from-audit.json>
# 4. Render the evidence-backed report for humans or the pipeline.
cyber-agent report --findings findings.json --audit-id <id> --format markdownExit codes stay machine-readable and separate from findings:
0 success · 1 audit/domain failure · 2 invalid input ·
3 policy denied · 4 security blocked · 5 provider/tool unavailable ·
6 verification inconclusive · 7 internal error.
Commands
cyber-agent doctor | audit | review | verify | status | report | extensions | mcpaudit takes --mode quick|standard|deep, --focus a,b,
--format human|json, and --output PATH. Only implemented options
exist — there are no --shell, --exec, --grant, --sudo,
--allow-write, or --bypass-policy flags, and no secret-valued flags
(use environment or secret providers).
Platform parity (evidence-first)
Live runtime proof, not CI-smoke claims. Method: real runners, real
installs, real CLI/MCP/HTTP/security batteries — green run
#37866150660.
Per-platform evidence lives in docs/evidence/:
Platform | Status |
Linux (ubuntu-24.04, Python 3.11 + 3.14) | Runtime PASS — 234/234 checks ×2 combos (wheel + sdist + PyPI origins; |
Windows (windows-2025, Python 3.11 + 3.14) | Runtime PASS — 234/234 ×2 combos; live PowerShell session NOT-EXECUTED, documented gap ( |
Android emulator (API 34, ARM64) via Termux | PASS — install + CLI/MCP/HTTP/security/E2E + independent review; verified working, not an officially supported platform ( |
macOS (arm64) | PASS — full suite 2720 passed / 0 failed + live CLI/MCP checks ( |
Honestly open (never inflated to PASS): Pi/Jan native delegation and
AnythingLLM adversarial-via-host are ENVIRONMENT-BLOCKED with reproducible
reasons; test-key rotation is LOW / OPEN (operator step). See
docs/evidence/POST-T021-final-review.md.
Limitations
Read-only analysis; no auto-remediation, no exploit capabilities, no scores-as-verdicts. Live-host interop beyond contract tests is environment-dependent (see host docs). Progress never gates security decisions; recovery never mutates policy, evidence, or findings.
FoundationSecurityAuditor.audit currently invokes locally installed Gitleaks
through the strict read-only tool boundary and returns redacted scanner
observations as evidence. It remains partial: Semgrep is intentionally not
run until offline rule configuration is verified, Trivy and OSV-Scanner are
not part of this local path, and finding classification/full control coverage
are not implemented. review and verify remain partial stubs. A successful
CLI process or an empty findings list is not a completed security assessment.
Verification and tests
make test # full suite (pytest, ~2 min)
python -m pytest tests/unit -q # unit scope onlyRelease-gate checks live in tests/release/; benchmark corpus sanity in
tests/unit/test_benchmark_*.py. Every material finding requires evidence;
verification precedes confirmation — see docs/03-security-methodology.md.
Reference documentation
Specs and contracts:
docs/(02-architecture.md,05-mcp-interface.md,06-cli-interface.md,07-python-api.md,08-tool-contracts.md).Host guides:
docs/integrations/(OpenCode, Pi, Hermes, Jan, AnythingLLM, generic MCP, delegation rules, security model).Threat model and guardrails:
docs/13-threat-model.md,docs/14-safety-guardrails.md,docs/policies/.Release provenance:
CHANGELOG.mdanddocs/evidence/.Contributing:
CONTRIBUTING.md.
Security vulnerabilities
Do not open a public issue for a suspected vulnerability. Report it
privately as described in SECURITY.md.
Contribute — help secure the agent era
Good first issues: host guides, benchmark cases, docs. PRs are reviewed against the same evidence bar the product enforces.
git clone https://github.com/SE-Emam/EMO-Cyber-Agent.git
cd EMO-Cyber-Agent && make checkSee CONTRIBUTING.md. If the project helps you, ⭐ star it —
discoverability is our growth engine.
License
Apache-2.0 — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Live behavioral security verifier, schema auditor, and trust oracle for A2A, MCP & x402 agents.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Read-only Remote MCP for externally grounded AI agent trust receipts.
Agent security: prompt injection, PII & secret scans, TLS/header/CORS audits, MCP checks. Free.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceRead-only MCP server that answers questions about turva.dev from its published data. Five tools return JSON: the service catalog with prices, contact and operator details, engagement principles and dated agent-readiness and security evidence with verification links. Connect over Streamable HTTP. You need no API key. The server does not scan other websites or run audits.MIT
- AlicenseNot gradedqualityBmaintenanceAudits MCP server configurations for security risks including capability inventory, SSRF, prompt injection, and drift detection. Works in read-only mode and can also be used as an MCP server to let AI agents audit their own attack surface.182 PyPI4MIT
- AlicenseNot gradedqualityDmaintenanceEnables authorized security auditing of AI-agent supply chains and agent-facing surfaces: deterministic local skill-bundle audits against eight attack patterns, secrets scanning, and scope-gated read-only recon of agent endpoints and MCP surfaces.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to run read-only AWS security audits and receive normalized, severity-ranked findings about account posture, such as stale access keys, missing MFA, public buckets, open security groups, and CloudTrail coverage.1125 PyPIMIT