drhalto/agentmako
by Various
Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.
MCP
drhalto/agentmako
Added 1 June 2026
Overview
A local-first MCP server that supplies coding agents with structured context packets, code and schema facts, and diagnostics. It uses a local SQLite store to persist and retrieve this information.
Best for
Best for
Developers building local coding agents that need structured context from their codebase
Use cases
- Providing coding agents with relevant code context during development
- Storing and retrieving schema facts for database-aware agents
- Delivering diagnostics to agents for error handling and debugging
How to use
Install
npm install -g agentmako Tools exposed
reef_askreef_statusreef_verifyreef_impactmako_helplive_text_searchlint_filestool_batchtool_searchcontext_packetdb_review_comment
Tested with
Claude Code, Cursor, Codex
Example client config
{\n "mcpServers": {\n "mako-ai": {\n "command": "agentmako",\n "args": ["mcp"]\n }\n }\n} Notes
A local-first MCP server that supplies coding agents with structured context packets, code and schema facts, and diagnostics. It uses a local SQLite store to persist and retrieve this information.
39 stars on GitHub. Last updated 2026-05-31. Licensed Apache-2.0.
Use cases
- Providing coding agents with relevant code context during development
- Storing and retrieving schema facts for database-aware agents
- Delivering diagnostics to agents for error handling and debugging
Pros
- Local-first design ensures data stays on the machine
- SQLite backend provides fast, reliable storage without external services
- Structured context packets help agents understand codebase context
Cons
- Small user base and limited community support
- Local-only storage may not suit team-based workflows
- Requires manual setup and configuration of the MCP server
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Local-first design ensures data stays on the machine
- SQLite backend provides fast, reliable storage without external services
- Structured context packets help agents understand codebase context
Cons
- Small user base and limited community support
- Local-only storage may not suit team-based workflows
- Requires manual setup and configuration of the MCP server
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
upstash/context7
Various
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
oraios/serena
Various
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
repowise-dev/repowise
Various
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
