Mcph MCP Server
@yawlabs/mcph
npm
v0.57.1
Source verified
Published by yawlabs — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. 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 |
| ✓ | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source |
| ✓ | inspection depth (source) — how much of the target the scan could see |
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 13
high Sensitive-source and external-sink co-existMTC-FLOW-004
Tools that read sensitive data ([mcp_connect_import]) and tools that can send data out ([mcp_connect_activate, mcp_connect_dispatch, mcp_connect_install, mcp_connect_exec]) are exposed together. An agent can move private data to the sink.
Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.
high Tool "mcp_connect_dispatch" exposes command/code executionMTC-CAP-001
Tool "mcp_connect_dispatch" appears to run shell commands or evaluate code (keyword "bash"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool mcp_connect_dispatch
high Tool "mcp_connect_install" exposes command/code executionMTC-CAP-001
Tool "mcp_connect_install" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool mcp_connect_install
high Tool "mcp_connect_exec" exposes command/code executionMTC-CAP-001
Tool "mcp_connect_exec" appears to run shell commands or evaluate code (keyword "exec"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool mcp_connect_exec
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:892`): 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 dist/index.js
medium Hardcoded egress to an external endpoint (dist/index.js)MTC-SRC-003
In the server's implementation (`dist/index.js:3267`): 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: fetch("https://registry.npmjs.org/@yawlabs/mcph/latest"
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 dist/index.js
medium Unconstrained URL/host parameter "server" on "mcp_connect_activate"MTC-CAP-007
Tool "mcp_connect_activate" takes a URL/host parameter "server" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool mcp_connect_activate · inputSchema.properties.server
medium Unconstrained URL/host parameter "url" on "mcp_connect_install"MTC-CAP-007
Tool "mcp_connect_install" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool mcp_connect_install · inputSchema.properties.url
medium Unconstrained command parameter "command" on "mcp_connect_install"MTC-CAP-006
Tool "mcp_connect_install" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool mcp_connect_install · inputSchema.properties.command
low Mutating tool "mcp_connect_dispatch" declares no destructiveHintMTC-CAP-005
Tool "mcp_connect_dispatch" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool mcp_connect_dispatch
low Mutating tool "mcp_connect_install" declares no destructiveHintMTC-CAP-005
Tool "mcp_connect_install" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool mcp_connect_install
low Mutating tool "mcp_connect_exec" declares no destructiveHintMTC-CAP-005
Tool "mcp_connect_exec" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool mcp_connect_exec
low Unconstrained path parameter "filepath" on "mcp_connect_import"MTC-CAP-008
Tool "mcp_connect_import" takes a path parameter "filepath" 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 mcp_connect_import · inputSchema.properties.filepath
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (18 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 |
|---|---|---|---|---|
v0.57.1 latest |
A 94/100 | 13 | 1.7.0 | 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 @yawlabs/mcph --onlineMore 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 Aemet MCP server.
Security scan results for the Agent MCP server.
Security scan results for the Agent Recorder MCP server.