McpKnowledge MCP Server

100+ MCP tools for AI agents: content metadata, trade intelligence, business-expertise analysis.

Tools

271

Last Updated

Jun 14, 2026

What is the McpKnowledge MCP Server?

The McpKnowledge MCP server gives AI agents structured, permission-aware access to McpKnowledge through the Model Context Protocol. With 271 pre-built actions, agents can read, create, and update McpKnowledge data on behalf of authorized users.

Willow ships the McpKnowledge MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how McpKnowledge is being used by every AI agent in your stack.

Tools

content_catalog

Browse the Gapup gold-standard content catalogue — video games, films, TV series and music. Returns franchises with their works (title, release year). When to use this tool: an agent needs structured, audited metadata for a cultural franchise, wants to resolve a title to a canonical entity, or browses a domain's catalogue before requesting enrichment. Inputs: a content domain and an optional case-insensitive name filter. Each franchise id can be passed to content_enrichment for its fine-grained tag profile.

content_enrichment

Return the enriched tag profile of a content entity — the Gapup moat. Each tag carries a facet (genre, theme, play-mode, perspective…), a confidence score, a corroboration score and its full provenance (which sources corroborated it, when). The response also carries an entity-level provenance block (average confidence, data freshness). When to use this tool: an agent has a franchise or work id (from content_catalog) and needs a fine-grained, machine-readable, verifiable characterisation for matching, recommendation, contextual targeting or analysis. Inputs: an entity id and its type.

content_discovery

Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') even when no literal tag matches. Results are verifiable: tag mode carries tag confidence/corroboration, semantic mode carries a similarity score; both carry entity freshness. When to use: an agent wants a domain-scoped shortlist by tag or by intent. Inputs: a domain plus either a tag or a free-text query.

content_similar

Find content entities similar to a given one. For embedded franchises this uses SEMANTIC vector similarity (pgvector) over the enrichment profile — surfacing entities that feel alike even when their tags differ literally. Falls back to shared enrichment-tag overlap for works or non-embedded entities. Each result carries a similarity score and its entity-level freshness/confidence (verifiable, sourced). When to use this tool: an agent wants recommendations or lookalikes for a franchise or work. Input: an entity_id and its type.

content_taxonomy

Return the enrichment taxonomy of a content domain — every tag grouped by facet (genre, theme, mood, play-mode…). When to use this tool: an agent needs the controlled vocabulary to filter, classify or query content. Input: a domain.

content_audience_profile

Return the audience targeting profile of a content entity — its enrichment tags reframed as audience facets with confidence, corroboration and full provenance (verifiable, sourced). The response also carries an entity-level provenance block (average confidence, data freshness). When to use this tool: an ad-tech or marketing agent needs a machine-readable, verifiable audience descriptor for a franchise or work. Input: an entity_id and its type.

content_provenance

Audit the full data provenance of a content entity — all its enrichment tags with their extraction source, corroboration score, source list and last verification date, plus an entity-level freshness summary. Use this tool before citing or relying on enriched content data in a high-stakes context (ad targeting, editorial, analysis). Inputs: entity_id (required) and entity_type (franchise or work).

content_compare

Compare the tag profiles of two content entities (franchises or works) and measure how similar they are. Returns a Jaccard similarity score, the list of shared tags, the tags unique to each entity, and a breakdown of shared tags by facet. When to use this tool: an agent needs to compare two franchises or works (e.g. 'how similar are Dark Souls and Elden Ring?', 'what do Street Fighter and Mortal Kombat have in common?', 'on which axes do these two games differ?'), find positioning overlap, identify cross-sell opportunities, or answer 'if you liked X you might like Y' questions backed by data. Works for any domain (video-games, music, film, tv).

content_ranking

Return the TOP-ranked content entities in a category, by a chosen criterion — the direct answer to superlative / decision queries: 'best video games', 'top RPGs', 'cheapest games', 'best value RPGs', 'best FPS playable right now', 'most popular music artists'. Criteria: critic_score, popularity, price, value (critic score per unit price). `direction` flips it (asc = cheapest/lowest first). `available_only` restricts to entities currently buyable. Sliceable by genre and release-year window; every result carries its score, price and source. When to use: an agent must produce a ranked shortlist to support a recommendation, a purchase or a 'what is the best X' decision.

ftg_market_gap

Return the import/production market-gap opportunities for a country — commodities where local demand outpaces local supply. Each opportunity carries the gap value (USD/year), the gap volume (tonnes/year), a 0-100 opportunity score and the potential margin. When to use this tool: an agent needs to know what a country structurally under-produces or over-imports, for trade sourcing, import/export or local-production investment decisions. Input: a country (ISO-2 code or name).

...

1–10 of 271 tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

Set Up Your McpKnowledge MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json

{
  "mcpServers": {
    "willow-mcpknowledge": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/mcpknowledge"
    }
  }
}

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "willow-mcpknowledge": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/mcpknowledge"
    }
  }
}

Claude Code

CLI

claude mcp add willow-mcpknowledge --transport http https://<org>.mcp-s.com/mcp/mcp/mcpknowledge

n8n

HTTP Request Node

{
  "url": "https://<org>.mcp-s.com/mcp/mcp/mcpknowledge",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for McpKnowledge

Willow adds the layer McpKnowledge and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

McpKnowledge MCP Server FAQ

What is the McpKnowledge MCP server?

The McpKnowledge MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write McpKnowledge data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's McpKnowledge MCP server different from the official one?

The official McpKnowledge MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the McpKnowledge MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the McpKnowledge MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in McpKnowledge, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which McpKnowledge actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow McpKnowledge MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved McpKnowledge MCP locally, you'll see it.

What does the McpKnowledge MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the McpKnowledge MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.