Pmcp (Consiliency) MCP Server
pmcp
PyPI
v1.19.4
Published by consiliency — 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 − 40.7 = 59. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −40.7 | Hardcoded JSON Web Token in server code ×4 MTC-SRC-008 | exfiltration |
2. Client adoption risk — 59 − 7 = 52. 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: 4 confirmed high findings → grade capped at D. 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 10
high Hardcoded JSON Web Token in server code (tests/test_auth.py)MTC-SRC-008
A live-looking JSON Web Token is hardcoded in `tests/test_auth.py:605`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: JSON Web Token: eyJh…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_auth.py
high Hardcoded JSON Web Token in server code (tests/test_cli.py)MTC-SRC-008
A live-looking JSON Web Token is hardcoded in `tests/test_cli.py:1830`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: JSON Web Token: eyJh…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_cli.py
high Hardcoded JSON Web Token in server code (tests/test_policy.py)MTC-SRC-008
A live-looking JSON Web Token is hardcoded in `tests/test_policy.py:315`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: JSON Web Token: eyJh…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_policy.py
high Hardcoded JSON Web Token in server code (tests/test_tools.py)MTC-SRC-008
A live-looking JSON Web Token is hardcoded in `tests/test_tools.py:5475`. Secrets in source ship to everyone who installs the package and are a direct credential leak.
Evidence: JSON Web Token: eyJh…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_tools.py
high Shell/command execution in server code (scripts/pipeline-bootstrap/run.mjs)MTC-SRC-002
In the server's implementation (`scripts/pipeline-bootstrap/run.mjs:18`): 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: child_process
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 scripts/pipeline-bootstrap/run.mjs
high Shell/command execution in server code (src/pmcp/cli.py)MTC-SRC-002
In the server's implementation (`src/pmcp/cli.py:215`): 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: spawn (
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/pmcp/cli.py
high Shell/command execution in server code (tests/test_client_manager.py)MTC-SRC-002
In the server's implementation (`tests/test_client_manager.py:3296`): 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 tests/test_client_manager.py
high Shell/command execution in server code (tests/test_phase4_e2e.py)MTC-SRC-002
In the server's implementation (`tests/test_phase4_e2e.py:50`): 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 tests/test_phase4_e2e.py
high Shell/command execution in server code (tests/test_singleton_lock_scope.py)MTC-SRC-002
In the server's implementation (`tests/test_singleton_lock_scope.py:61`): 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 tests/test_singleton_lock_scope.py
low Unconstrained path parameter "path" on "gateway.set_startup_policy"MTC-CAP-008
Tool "gateway.set_startup_policy" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool gateway.set_startup_policy · inputSchema.properties.path
Tools 26
Each tool and what it can reach — statically extracted from the published source.
gateway.set_startup_policyreads sensitive datagateway.auth_connectno sensitive capabilitygateway.cancelno sensitive capabilitygateway.catalog_searchno sensitive capabilitygateway.config_statusno sensitive capabilitygateway.connect_serverno sensitive capabilitygateway.describeno sensitive capabilitygateway.disconnect_serverno sensitive capabilitygateway.get_startup_policyno sensitive capabilitygateway.healthno sensitive capabilitygateway.invokeno sensitive capabilitygateway.list_pendingno sensitive capabilitygateway.provisionno sensitive capabilitygateway.provision_statusno sensitive capabilitygateway.refreshno sensitive capabilitygateway.register_discovered_serverno sensitive capabilitygateway.request_capabilityno sensitive capabilitygateway.restart_serverno sensitive capabilitygateway.search_registryno sensitive capabilitygateway.submit_feedbackno sensitive capabilitygateway.sync_environmentno sensitive capabilitygateway.tasks_cancelno sensitive capabilitygateway.tasks_getno sensitive capabilitygateway.tasks_listno sensitive capabilitygateway.tasks_resultno sensitive capabilitygateway.update_serverno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (26 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 |
|---|---|---|---|---|
v1.19.4 latest |
F 52/100 | 10 | 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 pmcp --online --registry pypiOther implementations of Pmcp 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More 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.