# Componecat **Category:** 💻 Developer Tools **Repository:** https://github.com/componecat/mcp **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/componecat ## Description Software component catalog: search your org's services, docs, APIs, dependencies, and ownership. ## Claude Desktop Quick Installation Heuristic fallback — verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low): ```json "mcpServers": { "componecat": { "command": "npx", "args": ["-y","componecat"] } } ``` ## Documentation & README # Componecat MCP Server **Componecat** is a software component catalog: a hierarchical, richly-typed registry of every system, service, and library your organization operates — with structured metadata, Git integration, hosted documentation, endpoint definitions, dependency relationships, and team ownership. Its [MCP](https://modelcontextprotocol.io) server gives AI agents the organizational context they're usually missing, so they can answer with *your* architecture instead of guessing. This repository is the public home of the server's MCP registry metadata ([`server.json`](server.json)) and the [`@componecat/mcp`](https://www.npmjs.com/package/@componecat/mcp) stdio bridge. The server itself is part of the hosted Componecat app: ``` https://app.componecat.ai/api/mcp ``` Registry name: **`ai.componecat/componecat`** · Transport: **Streamable HTTP** · Website: [componecat.ai](https://www.componecat.ai) · Docs: [docs.componecat.ai](https://docs.componecat.ai) Catalogs are private and organization-scoped, so the endpoint requires authentication (see [Authorization](#authorization)). You'll need a Componecat account — sign up at [app.componecat.ai](https://app.componecat.ai). ## Install [![Install in VS Code](https://img.shields.io/badge/VS_Code-Install_Componecat_MCP-0098FF?logo=githubcopilot&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=componecat&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapp.componecat.ai%2Fapi%2Fmcp%22%7D) [![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install_Componecat_MCP-24bfa5?logo=githubcopilot&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=componecat&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapp.componecat.ai%2Fapi%2Fmcp%22%7D&quality=insiders) ### VS Code Click an install badge above, or add to your `mcp.json`: ```json { "servers": { "componecat": { "type": "http", "url": "https://app.componecat.ai/api/mcp" } } } ``` ### Claude Code ```bash claude mcp add --transport http componecat https://app.componecat.ai/api/mcp ``` ### Claude.ai / Claude Desktop Add a custom connector: **Settings → Connectors → Add custom connector**, with URL `https://app.componecat.ai/api/mcp`. ### Cursor [Add to Cursor](cursor://anysphere.cursor-deeplink/mcp/install?name=componecat&config=eyJ1cmwiOiJodHRwczovL2FwcC5jb21wb25lY2F0LmFpL2FwaS9tY3AifQ==), or add to `~/.cursor/mcp.json`: ```json { "mcpServers": { "componecat": { "url": "https://app.componecat.ai/api/mcp" } } } ``` ### ChatGPT Add a connector in **Settings → Connectors** (developer mode) with the server URL `https://app.componecat.ai/api/mcp`. ### Stdio-only clients For clients that only speak stdio, the bridge in this repo proxies to the remote endpoint via [`mcp-remote`](https://www.npmjs.com/package/mcp-remote) (OAuth completes in your browser): ```json { "mcpServers": { "componecat": { "command": "npx", "args": ["-y", "@componecat/mcp"] } } } ``` Self-hosted Componecat instance? Point the bridge at it with `COMPONECAT_MCP_URL=https://your-instance.example.com/api/mcp`. ## Authorization Componecat implements the standard MCP authorization flow with OAuth 2.1: - **OAuth (authorization code + PKCE)** — the usual path for interactive clients. The client discovers the authorization server automatically; dynamic client registration is supported, so most clients need no manual setup. Device flow is available for clients that can't open a browser. - **Personal access tokens** — bearer tokens for scripts and non-interactive clients. Access is **scoped**: you grant an agent read or write access per resource category (catalog entities, teams, schema), and can scope a token down to specific entities. A read-only grant is enough for an agent that only needs context. ## Tools 60 tools, each annotated with read-only / destructive / idempotent hints so clients can gate confirmation appropriately. **Search & browse** `global_search` · `search_catalog` (full-text with typo tolerance, or a structured query language — `field:value`, AND/OR/NOT, comparisons, ranges) · `list_catalog_entities` · `get_catalog_entity` · `list_by_owner` · `list_entity_kind_definitions` · `get_current_organization` **Relationships & impact analysis** `get_relationships` · `get_relationship_kinds` · `add_relationship` · `remove_relationship` · `get_impact_analysis` (transitive downstream impact of a change) **Interfaces & endpoints** `get_interfaces` · `create_interface` · `update_interface` · `delete_interface` · `import_interface_spec` (import OpenAPI/AsyncAPI specs) **Documentation** `get_documentation` · `create_documentation_section` · `update_documentation_section` · `delete_documentation_section` · `list_documentation_links` · `create_documentation_link` · `update_documentation_link` · `delete_documentation_link` **Git-sourced documentation** (sections synced from Markdown in your repos) `configure_git_sourced_documentation` · `list_git_sourced_documentation` · `update_git_sourced_documentation` · `remove_git_sourced_documentation` · `sync_git_sourced_documentation` **Activity log** `list_activity_log_entries` · `add_activity_log_entry` · `delete_activity_log_entry` **Catalog maintenance** `create_catalog_entity` · `update_catalog_entity` · `delete_catalog_entity` · `update_entity_field_values` **Schema definitions** (entity kinds, custom fields, relationship kinds) `create_entity_kind_definition` · `update_entity_kind_definition` · `delete_entity_kind_definition` · `list_entity_field_definitions` · `create_entity_field_definition` · `update_entity_field_definition` · `delete_entity_field_definition` · `add_kind_field_assignment` · `update_kind_field_assignment` · `remove_kind_field_assignment` · `list_relationship_kind_definitions` · `create_relationship_kind_definition` · `update_relationship_kind_definition` · `delete_relationship_kind_definition` **Teams & ownership** `list_teams` · `get_team` · `create_team` · `update_team` · `delete_team` · `add_team_members` · `remove_team_member` **Product documentation** `list_componecat_documentation` · `read_componecat_documentation` — Componecat's own docs, so an agent can walk you through setup instead of guessing. The server also exposes the catalog as MCP **resources**: every entity is readable as its `componecat.yaml` descriptor, and a kind's entities can be listed without knowing the taxonomy in advance. ## Typical workflows - **Grounded code generation** — before generating code for a service, the agent looks up its kind, languages, interfaces, and conventions. - **Cross-service integration** — the agent follows `depends-on` edges, reads the target's interface spec, and writes a correct client. - **Impact analysis** — before a change, the agent traverses transitive relationships to see what breaks downstream. - **Ownership resolution** — the agent finds the owning team to route a review or an escalation. - **Documentation-grounded answers** — runbooks and architecture notes answer questions with your context, not generic guesswork. ## Links - [Product documentation](https://docs.componecat.ai) — including the [Connect AI agents](https://docs.componecat.ai/app/guides/connect-ai-agents/) guide - [Website](https://www.componecat.ai) - [REST API OpenAPI spec](https://app.componecat.ai/api/rest/v1/openapi.json) - [llms.txt](https://app.componecat.ai/llms.txt) ## License The contents of this repository (registry metadata and the stdio bridge) are [MIT licensed](LICENSE). The Componecat application itself is a hosted product and is not open source.