LangBot Space MCP Operations

LangBot Space (space.langbot.app) exposes an MCP server so user-facing AI agents can browse and search the marketplaces (plugins, MCP servers, skills) and rank live models for automated setup.

Endpoint

https://space.langbot.app/mcp

Transport: streamable HTTP (stateless, JSON responses). For a self-hosted Space instance: http://<host>:8383/mcp.

Authentication

Reuses the existing Personal Access Token (PAT) — the same token the lbp CLI uses. Create one in your Space account (Profile → Personal Access Tokens), then send it as a Bearer token:

Authorization: Bearer <your-pat>

Requests without a valid PAT get 401 Unauthorized.

Client configuration

{
  "mcpServers": {
    "langbot-space": {
      "url": "https://space.langbot.app/mcp",
      "headers": { "Authorization": "Bearer <your-pat>" }
    }
  }
}

Tool surface

list_* and search_* are paged (page, page_size). get_* takes author + name. The tool surface mirrors the REST endpoints under /api/v1/marketplace/*; select_models mirrors /api/v1/models/selection. All tools are read-only.

How to use

1. Create a PAT in your Space account settings.
2. Point your MCP client at https://space.langbot.app/mcp with the Bearer PAT.
3. Use search_plugins / search_mcp_servers / search_skills to find items, then get_* for details (e.g. to obtain author/name for installation in LangBot itself).
4. For automatic local-agent setup, call select_models (optionally with category) and choose the first compatible item. Ordering is latest probe state (available, unprobed, unavailable), then Space recommendation. Each item includes availability.up, last_probed_at, latency, and HTTP status.

Runner usage recommendations

Use search_plugins with runner_usage: "agent" for Agent, pipeline, and setup-wizard recommendations, or runner_usage: "event" for event processors. The component kind remains Runner. Only these two exact values are accepted; omit the optional field to preserve unfiltered browsing.

{"query":"", "runner_usage":"agent", "page":1, "page_size":100}

Plugin results include latest_version and runner_usages: string[], the explicit union of usages in that latest installable version. Only recommend a plugin when this array explicitly contains the target usage. Missing, empty, malformed, or unknown usages must never mean agent-compatible. Event-only plugins must never enter Agent recommendations. Empty filtered results are valid while legacy packages await corrected releases; never remove the filter to fill a recommendation list.

REST callers use runner_usage on both POST /api/v1/marketplace/extensions/search and the compatibility POST /api/v1/marketplace/plugins/search; preserve it during fallback. Add "type_filter":"plugin", "component_filter":"Runner" on the unified endpoint. Usage is ANDed with other filters before pagination and total; MCP/Skill items do not match. Invalid REST values return HTTP 400.

Open the same filter in the webpage: https://space.langbot.app/market?type=plugin&component=Runner&runner_usage=agent (or runner_usage=event). Switch All / Agent / Event in the Runner usage row.

Implementation & maintenance (for Space developers)

• Server: internal/controller/mcp/server.go (official Go MCP SDK github.com/modelcontextprotocol/go-sdk). Tools call the service layer (PluginService, MCPService, SkillService, ModelStatusService) directly.
• Mount: internal/controller/api.go at /mcp and /mcp/*any.
• Auth: PAT via AccountService.ValidatePersonalAccessToken.
• Docs: docs/MCP_SERVER.md.

When you add, remove, or change a marketplace API endpoint that should be agent-accessible, update the corresponding MCP tool and this skill. The MCP tool surface and the API must stay aligned (see AGENTS.md).

Pitfalls

• The PAT prefix is lbpat_ (Space), distinct from LangBot's lbk_ API keys.
• This server is read/browse only; it does not publish or modify marketplace items. Use the web UI or REST API (with appropriate auth) for that.