Autodev X MCP Server
autodev-x
PyPI
v0.1.0a6
Published by merchloubna70-dot — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 22 = 78. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −22 | Hardcoded GitHub token in server code MTC-SRC-008 | exfiltration |
2. Client adoption risk — 78 − 7 = 71. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
| ✓ | inspection depth (source) — how much of the target the scan could see |
Grade capped: 1 confirmed high finding → grade capped at C. A hard gate overrides the point total — no amount of clean surface buys back a confirmed catastrophe.
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 16
high Reads a sensitive credential path or dumps the environment (src/autodev/mcp_server/path_safety.py)MTC-SRC-006
In the server's implementation (`src/autodev/mcp_server/path_safety.py:31`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/mcp_server/path_safety.py
high Reads a sensitive credential path or dumps the environment (tests/integration/test_mcp_path_secret_denial.py)MTC-SRC-006
In the server's implementation (`tests/integration/test_mcp_path_secret_denial.py:88`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/integration/test_mcp_path_secret_denial.py
high Hardcoded GitHub token in server code (tests/unit/test_secret_redaction.py)MTC-SRC-008
A live-looking GitHub token is hardcoded in `tests/unit/test_secret_redaction.py:80`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: GitHub token: ghp_…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/unit/test_secret_redaction.py
high Dynamic code execution in server code (src/autodev/agents/adversarial_reviewer.py)MTC-SRC-001
In the server's implementation (`src/autodev/agents/adversarial_reviewer.py:40`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eval(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/agents/adversarial_reviewer.py
high Shell/command execution in server code (src/autodev/adapters/a2a/transports/local_shell.py)MTC-SRC-002
In the server's implementation (`src/autodev/adapters/a2a/transports/local_shell.py:70`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/adapters/a2a/transports/local_shell.py
high Shell/command execution in server code (src/autodev/adapters/mcp_client.py)MTC-SRC-002
In the server's implementation (`src/autodev/adapters/mcp_client.py:118`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.Popen(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/adapters/mcp_client.py
high Shell/command execution in server code (src/autodev/adapters/opus_adapter.py)MTC-SRC-002
In the server's implementation (`src/autodev/adapters/opus_adapter.py:84`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/adapters/opus_adapter.py
high Shell/command execution in server code (src/autodev/agents/adversarial_reviewer.py)MTC-SRC-002
In the server's implementation (`src/autodev/agents/adversarial_reviewer.py:38`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: shell=True
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/agents/adversarial_reviewer.py
high Shell/command execution in server code (src/autodev/agents/document_project.py)MTC-SRC-002
In the server's implementation (`src/autodev/agents/document_project.py:23`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/agents/document_project.py
high Shell/command execution in server code (src/autodev/agents/investigator.py)MTC-SRC-002
In the server's implementation (`src/autodev/agents/investigator.py:234`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/agents/investigator.py
high Shell/command execution in server code (src/autodev/agents/security_reviewer.py)MTC-SRC-002
In the server's implementation (`src/autodev/agents/security_reviewer.py:28`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/agents/security_reviewer.py
high Shell/command execution in server code (src/autodev/context_providers/search_provider.py)MTC-SRC-002
In the server's implementation (`src/autodev/context_providers/search_provider.py:40`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/context_providers/search_provider.py
high Shell/command execution in server code (src/autodev/coverage_gate.py)MTC-SRC-002
In the server's implementation (`src/autodev/coverage_gate.py:26`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: exec(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/coverage_gate.py
high Shell/command execution in server code (src/autodev/executors/_fs_observer.py)MTC-SRC-002
In the server's implementation (`src/autodev/executors/_fs_observer.py:24`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: subprocess.run(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/autodev/executors/_fs_observer.py
medium Hardcoded egress to an external endpoint (tests/integration/test_parallel_review_5sections.py)MTC-SRC-003
In the server's implementation (`tests/integration/test_parallel_review_5sections.py:49`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: requests.get('http://example.com'
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/integration/test_parallel_review_5sections.py
low Dynamic code execution in packaging/dev tooling (tests/unit/test_adversarial_reviewer.py)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/unit/test_adversarial_reviewer.py:95`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eval(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/unit/test_adversarial_reviewer.py
Tools 9
Each tool and what it can reach — statically extracted from the published source.
autodev_classify_inputno sensitive capabilityautodev_create_prdno sensitive capabilityautodev_deliver_projectno sensitive capabilityautodev_list_runsno sensitive capabilityautodev_release_checkno sensitive capabilityautodev_reportno sensitive capabilityautodev_roundtableno sensitive capabilityautodev_run_issueno sensitive capabilityautodev_scanno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (9 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.1.0a6 latest |
C 71/100 | 16 | 1.8.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan autodev-x --online --registry pypiMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Agent MCP server.