The External Brain for AI Coding Agents — see what your LLM can't see
# Blindspot MCP — The External Brain for AI Coding Agents
> **See what your LLM can't see.** Early release — Laravel production-tested, 15 more framework plugins in alpha.
**v0.1.5** — [Report bugs](https://github.com/umuterdal/blindspot-mcp/issues) | [Contribute](https://github.com/umuterdal/blindspot-mcp/pulls)
[](https://pypi.org/project/blindspot-mcp/)
[](https://pypi.org/project/blindspot-mcp/)
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
### What's New in v0.1.5
- Fail-closed safety orchestration (`safe_implement`, `safe_refactor`, `safe_optimize`, `safe_migrate`, `safe_fix`)
- Language adapter matrix (`run_diff_aware_quality_matrix`) with per-language syntax/static/format/test gates
- Universal completion gate (`run_universal_completion_gate`) and bounded auto-fix loop for post-write verification
- Governance and release controls (policy approvals, break-glass, rollout, backup/DR, release readiness)
- Mandatory release evidence reporting (`conformance_matrix`, `gate_evidence_pack`, `kpi_report`, `open_risk_register`)
- CI safety release gate workflow and expanded test coverage for safety/governance and Laravel route validation
### Install
```bash
pip install blindspot-mcp
```
**Claude Code** — add to `~/.cursor/settings.json`:
```json
{
"mcpServers": {
"blindspot": {
"command": "blindspot-mcp",
"args": ["--project-path", "/path/to/your/project"]
}
}
}
```
**Cursor / VS Code** — add to `.cursor/mcp.json`:
```json
{
"mcpServers": {
"blindspot": {
"command": "blindspot-mcp",
"args": ["--project-path", "."]
}
}
}
```
---
## Why Blindspot Exists
I built Blindspot because I was frustrated. I use AI coding agents Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.