.png)
CostAffective-MCP
@okyashgajjar
About CostAffective-MCP
Intelligent repository context for AI coding assistants. Provides code search, symbol lookup, call graphs, and reference tracking via MCP. Uniquely designed to minimize prompt-cache costs in long sessions stash/recall/remember tools keep large content out of context until needed,
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"costaffective": {
"command": "costaffective",
"args": [
"serve"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is CostAffective-MCP?
CostAffective-MCP is a local MCP server that optimizes token usage for AI coding agents by providing efficient, token-budgeted access to repository symbols, code, and context. It integrates with any stdio MCP client like Claude Code, Cursor, or Cline, and is designed for developers using AI coding agents in long sessions to reduce prompts and costs.
How to use CostAffective-MCP?
Install via the provided curl script or build from source with Go 1.25+ and a C compiler. Configure your MCP client with the command costaffective and argument serve. The server will automatically index your repository on first access and provide 11 MCP tools for code retrieval, context control, and maintenance.
Key features of CostAffective-MCP
- Semantic code search by natural language query
- Symbol definition lookup and full implementation retrieval
- Finds references and callers for any symbol
- Persist durable facts
More Other MCP servers
FastMCP v2 π
jlowinπ The fast, Pythonic way to build MCP servers and clients.
XcodeBuildMCP
cameroncookeA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Core Philosophy: Connect, Unify, Respond
mindsdbDelegate anything. It comes back done.
MCP Go π
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
Comments