{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_wywmcpv5ak2k","handle":"blindspot-mcp","url":"https://wellknown.network/agents/blindspot-mcp","links":{"self":"https://wellknown.network/agents/blindspot-mcp/record.json","html":"https://wellknown.network/agents/blindspot-mcp","markdown":"https://wellknown.network/agents/blindspot-mcp/record.md","api":"https://wellknown.network/api/v1/agents/blindspot-mcp","status":"https://wellknown.network/api/v1/agents/blindspot-mcp/status","claim":"https://wellknown.network/agents/blindspot-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/blindspot-mcp/claim.json","badge":"https://wellknown.network/agents/blindspot-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/blindspot-mcp/history","tools":"https://wellknown.network/api/v1/agents/blindspot-mcp/tools"},"ard":{"identifier":"urn:air::server:blindspot-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"blindspot-mcp","summary":"The External Brain for AI Coding Agents — see what your LLM can't see. Provides instant, structured intelligence about your entire codebase without reading files into the AI's context window.","description":"# Blindspot MCP\n\nBlindspot is a local, general-purpose context engine for AI coding agents.\n\nIt exists for one job:\n\n- help the agent understand a project\n- help the agent understand symbols and relationships\n- help the agent estimate change impact before editing\n- do this across different languages and project layouts\n\nBlindspot is intentionally small. It is not trying to be a deployment system, policy engine, rollout manager, or autonomous edit platform.\n\n## Why\n\nMost agents can edit files, search text, and run commands.\nWhat they usually lack is a compact, reusable understanding layer for:\n\n- project structure\n- symbol ownership\n- callers and references\n- inheritance and composition\n- likely blast radius of a change\n\nThat is the gap Blindspot fills.\n\nPaid context engines already proved this model is useful. Blindspot is the local and reusable alternative.\n\n## Design Goals\n\n- Small MCP surface\n- Works across languages and frameworks\n- Gives structured context instead of file dumps\n- Helps any agent write better code with fewer blind edits\n- Stays useful even when framework-specific intelligence is missing\n\n## Language Coverage\n\nBlindspot keeps one public API and improves the engine underneath it.\n\n- Strong support: Python, PHP, JavaScript, TypeScript, Go\n- Solid project-structure and syntax-aware support: Dart / Flutter, React Native, Node.js\n- Additional generic support: Java, Kotlin, C#, Ruby, Rust, mixed repos\n\nThe contract does not change per language. `get_context(...)` stays the same; only the quality of the internal enrichment improves.\n\n## Core Tools\n\nBlindspot now exposes only the core context-engine surface:\n\n- `set_project_path`: call once to bind Blindspot to the repo\n- `get_project_snapshot`: one-shot repo overview at session start\n- `get_context`: main entrypoint for file, symbol, relationship, and impact context\n- `get_symbol_body`: exact symbol metadata or bounded source excerpt\n- `get_edit_region`: small numbered excerpt around a symbol or line r…","publisher":{"name":"Umut Erdal","url":null},"homepage":"https://github.com/umuterdal/blindspot-mcp","repository":"https://github.com/umuterdal/blindspot-mcp","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp","model-context-protocol","ai","coding-assistant","code-intelligence","context-engine","refactoring","code-analysis","claude","cursor","copilot"],"pricing":null,"endpoints":[{"url":"pypi:blindspot-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"code.generation","name":"Code Generation","confidence":1,"provenance":"derived"},{"slug":"code.refactoring","name":"Refactoring","confidence":1,"provenance":"declared"}],"categories":["code"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"blindspot-mcp","registry":"pypi","observedAt":"2026-10-21T18:28:08.821Z","publishedAt":"2026-04-17T03:05:41.741205Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"blindspot-mcp","url":"https://pypi.org/project/blindspot-mcp/","firstSeenAt":"2026-09-09T10:27:27.296Z","fetchedAt":"2026-10-21T18:26:50.640Z","normalizedAt":"2026-10-21T18:26:50.640Z"}]},"firstSeenAt":"2026-09-09T10:27:27.296Z","updatedAt":"2026-10-21T18:28:08.821Z"}