Spiderbrain

ai.spiderbrainPublished by spiderbrain.aiOfficial publisherv0.2.3Updated Oct 27, 2026

Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Serves a committed, source-free understanding layer for a repository, letting an assistant trace change impact, blast radius and file paths with receipts.

What you can do
  • Query a repository's committed understanding layer for what a change reaches, including blast radius for a specific file or the current git diff.
  • Identify load-bearing files and trace how one file reaches another.
  • Verify that the understanding folder is untampered, usable as a CI gate.
  • Optionally ask the cloud why-layer for rationale behind the code, when an API key is configured.
  • Fall back to a public registry when the repository has no committed understanding folder.
When to use it
Useful when an assistant works on a codebase that already has a committed understanding folder and needs to reason about change impact, dependencies or design rationale rather than just reading files. Also suited to CI checks that verify the folder is intact.
Requirements
Runs as a remote endpoint or locally via npx (Node.js). SPIDERBRAIN_ROOT must be set to the absolute path of the repository containing a committed understanding folder. OAuth is supported for clients that implement it; otherwise an Authorization header or the SPIDERBRAIN_API_KEY variable is needed for the cloud why-layer. SPIDERBRAIN_REGISTRY optionally overrides the public registry URL.
Before you install
SPIDERBRAIN_API_KEY is a secret used for the cloud why-layer and is sent to the vendor's service; the structural tools work without it. If SPIDERBRAIN_ROOT is not set, the server silently serves the wrong directory and reports no understanding layer instead of erroring. Creating the understanding folder writes files into the repository and requires an account and key.

Installation

In SourceWeft

  1. Open Spiderbrain in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.spiderbrain%2Fspiderbrain/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "spiderbrain": {
      "type": "http",
      "url": "https://mcp.spiderbrain.ai/mcp"
    }
  }
}

README

spiderbrain

A committed understanding layer for your repo, and the one command to work with it. A repo tells an AI agent what the code is; it never tells it what matters, what a change reaches, or why anything was built the way it was. spiderbrain fixes that.

Give a repo understanding

export SPIDERBRAIN_API_KEY=sb_live_...     # https://spiderbrain.ai/dashboard?tab=keysnpx spiderbrain create

Writes a source-free .spiderbrain/ folder and an AGENTS.md block. Commit both.

Read a repo's understanding (no account needed)

When a repo has a .spiderbrain/ folder, any agent or developer can use it offline:

npx spiderbrain mcp --root .        # an MCP server for Claude Code / Cursornpx spiderbrain blast src/db.ts     # what a change here reachesnpx spiderbrain impact              # what your current git diff reachesnpx spiderbrain keystones           # the load-bearing filesnpx spiderbrain path a.ts b.ts      # how one file reaches anothernpx spiderbrain verify --allow-stale   # folder untampered? (CI gate)

An MCP client's working directory is usually not your repository, so pass the repo explicitly with --root <path>, --root=<path>, or the SPIDERBRAIN_ROOT environment variable. Without it the server serves the working directory and reports that no understanding layer was found, which is a wrong answer rather than an error.

Every command takes --json (exit codes: 0 ok, 1 failed, 2 usage, 3 no understanding). No committed folder? The reader falls back to the public registry when the repo's origin has an unofficial brain there.

The pieces

spiderbrain is a thin dispatcher over two independently installable packages:

A CI job that only publishes understanding can depend on @spiderbrain/create alone; an MCP config that only reads can point at @spiderbrain/read. spiderbrain is what you type when you just want the thing.

License

MIT.

Source: spiderbrain/README.md at commit 6e8b121

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.2.3LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts