
Brain Scanner
Review what your coding agent changed and decided, then queue its next step
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 0.8.3
- Listing updated
- today
About Brain Scanner
Brain Scanner is an MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
Brain Scanner keeps a hosted record of what AI coding agents do in a project, so a failed session can be picked up without retyping a recap. After connecting Claude Code or Codex through the hosted MCP connector, the agent submits structured project information within its permissions, and the dashboard shows it back.
A session review shows the agent's summary, recorded decisions, checks that failed or passed, blockers and any file diffs the agent submitted. Beyond sessions, the site describes a graph of files, symbols and subsystems, implementation progress estimates shown with evidence ranges and confidence, a folder explorer, and reports with linked open bugs.
Follow-up work is queued as scoped tasks that the agent can read through MCP when asked to continue. Queued tasks can be edited or cancelled in the dashboard. Pricing is not stated.
Install
Run in a terminal
claude mcp add --transport http brain-scanner https://brainscanner.dev/mcp/v2Add to Settings → Connectors → Add custom connector
https://brainscanner.dev/mcp/v2Add to ~/.cursor/mcp.json
{
"mcpServers": {
"brain-scanner": {
"url": "https://brainscanner.dev/mcp/v2"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"brain-scanner": {
"type": "http",
"url": "https://brainscanner.dev/mcp/v2"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"brain-scanner": {
"serverUrl": "https://brainscanner.dev/mcp/v2"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"brain-scanner": {
"type": "http",
"url": "https://brainscanner.dev/mcp/v2"
}
}
}What it does
- Session review
- See an agent's summary, decisions, checks, blockers and submitted diffs.
- Decision record
- Earlier decisions stay on file so they need not be repeated.
- Project graph
- Files, symbols and subsystems mapped into one connected view.
- Progress estimates
- Implementation estimates shown beside evidence range and confidence.
- Task queue
- Queue the next step for the agent to pick up through MCP.
Good for
- Recover context after a coding agent breaks something
- Check which files an agent changed in a session
- Keep architecture decisions visible across sessions
- Queue a fix for an agent to continue later
Brain Scanner FAQ
Which agents does it work with?
The site names Claude Code and Codex, connected through MCP.
Does it show code diffs?
Yes, file diffs appear when the agent submits them.
Can queued tasks be changed?
Yes, they can be edited or cancelled from the dashboard.
How do I add Brain Scanner to Claude Code?
Run this command in your terminal: claude mcp add --transport http brain-scanner https://brainscanner.dev/mcp/v2
What are the best alternatives to Brain Scanner?
The closest alternatives to Brain Scanner are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Brain Scanner

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools