C

npm:@usecomposer/mcp

https://www.npmjs.com/package/@usecomposer/mcp
75/100 · MCP Trust Grade · checked 3h ago · MCP 0.1.7

What it offers — 16 tools · Developer Tools

get_graph

Get the full architecture diagram -all nodes and edges.

get_node

Get full details for a single node including connected edges.

upsert_node

Create or update an architecture node on the diagram.

upsert_edge

Create or update a connection between two nodes.

define_api

Define API endpoints on a service node (full replacement).

delete_element

Delete a node or edge from the diagram.

link_path

Link a node to a file or folder path in the codebase.

get_guide

Get the Composer reference guide -node types, edge protocols, completeness criteria, and available tools. Call this BEFORE creating or modifying any n

plan_import

Get the step-by-step workflow for importing a codebase into Composer. Call this when about to scan a repository and recreate its architecture as a dia

search_graph

Search the diagram for nodes and edges matching a keyword. Searches names, descriptions, tags, paths, endpoints, entities, edge labels, and data flows

verify_diagram

Check the diagram for completeness issues -orphaned nodes, missing endpoints/entities/descriptions, edges without data_flow. Call after building to ca

list_diagrams

List all diagrams accessible to you. Call this first to find which diagram to work on.

create_diagram

Create a new diagram and auto-select it for this session.

select_diagram

Select which diagram to work on for this session.

rename_diagram

Rename the currently selected diagram.

get_screenshot

Get a base64-encoded PNG thumbnail of the diagram captured during the last auto-save in the Composer UI.

Spec / packaging20%100
Security (OWASP MCP)30%25
Maintenance / popularity20%100
Tool hygiene15%95
Transparency / provenance15%90

Findings

WARNMCP08 References sensitive file paths / environment secrets.
INFO Static analysis of npm package @usecomposer/mcp@0.1.7 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.
Grade another server

We re-grade npm:@usecomposer/mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:@usecomposer/mcp grade C
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade C · wmcp.sh
[![MCP Trust Grade C](https://wmcp.sh/mcp/grade/npm%3A%40usecomposer%2Fmcp/badge.svg)](https://wmcp.sh/mcp/grade/npm%3A%40usecomposer%2Fmcp)
<a href="https://wmcp.sh/mcp/grade/npm%3A%40usecomposer%2Fmcp"><img src="https://wmcp.sh/mcp/grade/npm%3A%40usecomposer%2Fmcp/badge.svg" alt="MCP Trust Grade C · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.