What is the Spiderbrain MCP server?
Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.
How to install Spiderbrain
Copy-paste configuration for popular MCP clients.
SPIDERBRAIN_ROOTrequiredAbsolute path to the repository to serve, which must already contain a committed .spiderbrain/ folder. Set this: an MCP client's working directory is usually not your repository, and without it the server serves the working directory and reports that no understanding layer was found. Equivalent to passing --root.
SPIDERBRAIN_API_KEYsecretOptional. Enables the cloud why-layer used by the sb_ask tool. The structural tools work offline without it.
SPIDERBRAIN_REGISTRYOptional. Base URL of the public brain registry this server consults on the first tool call when the repository has no committed .spiderbrain/ folder. Defaults to https://spiderbrain.ai/registry.
AuthorizationsecretOptional. This server implements the MCP OAuth flow (dynamic client registration and PKCE), so a client that supports it can connect with no token: leave this blank. For headless or CLI use, set 'Bearer sb_live_...' with an API key from your Spiderbrain dashboard. Either way the hosted brain requires an existing Spiderbrain account with an uploaded brain.
Related MCP servers
SpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)
View repository →SpiderIQ Leads: lead-gen MCP (jobs, campaigns, IDAP, Maps, People, Verify, company intel, spiderPR)
View repository →SpiderIQ Mail: SpiderMail mailboxes, messages, threads, send, compose for AI agents
View repository →SpiderIQ Media: SpiderMedia files, videos, per-tenant media catalog (read)
View repository →SpiderIQ Publish: content platform MCP (pages, posts, templates, components, domains, media)
View repository →Agent memory that refuses to guess: evidence-gated recall, exact-source reads, verifiable deletion.
