Callwright MCP Server
callwright
npm
v1.0.4
Published by topness — 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.
A voice agent that places phone calls (reservations, appointments, inquiries) on your behalf, shaped by LLM direction + grounding. Runs fire-and-forget on Retell; an MCP server lets an LLM shape the grounding before each call.
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 − 4 = 96. 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 |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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 2
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get_call_outcome]) co-exist with external-action tools ([configure_notifications]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get_call_outcome] → sinks [configure_notifications]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get_call_outcome → configure_notifications
medium Hardcoded egress to an external endpoint (learn.js)MTC-SRC-003
In the server's implementation (`learn.js:25`): 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: () { const r = await fetch(`https://api.retellai.com/v2/get-call/${callId}`, { headers: { Authorization: `Bearer
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 learn.js
Tools 19
Each tool and what it can reach — statically extracted from the published source.
configure_notificationsnetwork egressget_call_outcomeingests untrusted inputadd_languageno sensitive capabilityadd_scenario_aliasno sensitive capabilityconfigureno sensitive capabilitycreate_profileno sensitive capabilityget_setup_statusno sensitive capabilitylearn_from_callno sensitive capabilitylist_candidatesno sensitive capabilitylist_languagesno sensitive capability
Show 9 more tools ↓
list_recent_callsno sensitive capabilitylist_retriesno sensitive capabilitylist_scenariosno sensitive capabilitylist_voicesno sensitive capabilityplace_callno sensitive capabilityreject_candidateno sensitive capabilityremove_languageno sensitive capabilityupdate_languageno sensitive capabilityverify_languageno sensitive capability
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 (19 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 1
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 |
|---|---|---|---|---|
v1.0.4 latest |
A 96/100 | 2 | 1.13.0 | 2026-09-08 |
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 callwright --onlineMore in API Development
Adapters for the FrontMCP framework
Transcend MCP Server — Admin tools.
Transcend MCP Server — Assessments tools.
MCP Server for Bling
MCP Server for Blogger API
Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.