Wiro MCP Server

@wiro-ai/wiro-mcp npm v1.3.0 Source verified

Published by wiroai — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.

Official MCP server for Wiro AI — access all AI models on Wiro from Cursor, Claude, Windsurf, and any MCP-compatible AI assistant

View on npm ↗ Repository ↗ Raw report (JSON) ↗

Trust grade

97/100

Last scanned 2026-09-08 get badge →

Trust

A · 97/100

Adoption risk for you: the threat score, then adjusted down for blast radius, publisher verification and how much the scan could see. Deterministic; every point is auditable.

Capability

Moderate

Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.

Coverage

Source

How much the scan could actually inspect. Shallow coverage is stated, never hidden.

A Why this grade threat 100 − adoption risk = 97/100

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 − 3 = 97. 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

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 ([explore, search_models]) co-exist with external-action tools ([upload_file]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.

Evidence: untrusted [explore, search_models] → sinks [upload_file]

Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.

Location: flow explore → upload_file

medium Unconstrained URL/host parameter "url" on "upload_file"MTC-CAP-007

Tool "upload_file" 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 upload_file · inputSchema.properties.url

Tools 13

Each tool and what it can reach — statically extracted from the published source.

exploreingests untrusted input
search_modelsingests untrusted input
upload_filenetwork egress
cancel_taskno sensitive capability
get_model_schemano sensitive capability
get_taskno sensitive capability
get_task_priceno sensitive capability
kill_taskno sensitive capability
list_tasksno sensitive capability
recommend_modelno sensitive capability

Show 3 more tools ↓

run_modelno sensitive capability
search_docsno sensitive capability
wait_for_taskno 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 (13 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 5

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
`v1.3.0` latest	A 97/100	2	1.13.0	2026-09-08
`v1.2.3`	A 97/100	2	1.13.0	2026-08-28
`v1.2.2`	A 97/100	2	1.12.1	2026-08-23
`v1.2.1`	A 97/100	2	1.12.1	2026-08-20
`v1.1.4`	A 97/100	1	1.12.1	2026-08-01

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.

Markdown (GitHub README)

[![MCP Trust Score](https://mcptrustchecker.com/registry/wiro-ai-wiro-mcp/badge.svg)](https://mcptrustchecker.com/registry/wiro-ai-wiro-mcp)

HTML

<a href="https://mcptrustchecker.com/registry/wiro-ai-wiro-mcp"><img src="https://mcptrustchecker.com/registry/wiro-ai-wiro-mcp/badge.svg" alt="MCP Trust Score" height="20"></a>

Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/wiro-ai-wiro-mcp/badge.json via https://img.shields.io/endpoint?url=…

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 @wiro-ai/wiro-mcp --online

Use the free API → How scoring works

More in AI & Agents

Agent Source verified npm

@aauth/mcp-agent

Authenticated MCP transport with HTTP Signatures for AAuth agents

AI & Agents Score 100/100 1 finding 1.4k/wk Cap. Minimal

Agent Claim Source verified npm

@vk0/agent-claim-mcp

Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.

AI & Agents Score 100/100 0 findings 66/wk Cap. Minimal

Agent Comm Source verified npm

agent-comm

Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events

AI & Agents Score 100/100 2 findings 159/wk Cap. Minimal

Agent Comm Source verified npm

@jerfowler/agent-comm-mcp-server

MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility

AI & Agents Score 100/100 0 findings 17/wk Cap. Minimal

Agent Mcp Manager Source verified npm

agent-mcp-manager

Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.

AI & Agents Score 100/100 0 findings 234/wk Cap. Minimal

Agent Mesh Source verified npm

@reaatech/agent-mesh-mcp-server

MCP server layer exposing agent-mesh orchestrator as an MCP agent

AI & Agents Score 100/100 0 findings 9/wk Cap. Minimal