MCPHub

0 serversUpdated Aug 28, 2026

ServersTrendingCategories
MCPHub

Catalog

  • Servers
  • Trending
  • Categories

Company

  • About

Shout out

  • Formatly
  • Hirime

Searchable catalog of Model Context Protocol servers. Find tools that connect your AI assistant to the services and data you use.

PrivacyTerms

© 2026 MCPHub

Servers/Code Execution/tokensave
Code ExecutionOfficial
T

tokensave

Supercharge your Agent with Semantic Code Intelligence and save 💰 in the process!

603 starsUpdated Aug 24, 2026
View on GitHub

Ads

Overview

AI coding agents waste tokens exploring codebases. Every grep, glob, and file read costs money. On complex tasks, agents spawn multiple Explore sub-agents that scan hundreds of files just to build context. tokensave gives agents a pre-indexed semantic knowledge graph. Instead of scanning files, the agent queries the graph and gets instant, structured answers -- the right symbols, their relationships, and source code, in one call. Without tokensave: Agents use grep, glob, and Read to scan files -- many API calls, high token usage.

Installation

Installation instructions are not available yet.

Configuration

{
  "mcpServers": {
    "tokensave": {
      "command": "/path/to/tokensave",
      "args": ["serve"]
    }
  }

Capabilities

  • Semantic code search

    Ask your AI to find code by meaning, e.g. "authentication" returns `login`, `validateToken`, and `AuthService` via `tokensave_search`.

  • Impact analysis

    Trace callers, callees, and the full impact radius of any symbol before making changes using `tokensave_callers` and `tokensave_impact`.

  • Context building

    Retrieve entry points, related symbols, and code snippets in one call with `tokensave_context`, replacing multi-step file exploration.

  • Cross-branch queries

    Search symbols or diff code graphs between branches without switching checkouts via `tokensave_branch_search` and `tokensave_branch_diff`.

  • Atomic code edits

    Apply unique-anchor string replacements, multi-replace, or AST rewrites with `tokensave_str_replace` and `tokensave_insert_at`, auto re-indexing after writes.

  • Session memory

    Persist design decisions and code-area context across sessions with `tokensave_record_decision` and recall them via `tokensave_session_recall`.

Tags

  • coding-agent
  • development
  • ai-agent

Related MCP servers

C

Context7 MCP

Official

Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.

61.3kCode ExecutionUpdated Today
C

Chrome DevTools MCP

Official

Official Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.

49.9kCode ExecutionUpdated Today
M

Mastra/mcp

Official

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

27.5kCode ExecutionUpdated Today

GitHub MCP Server

Official

Connect your AI assistant to GitHub repositories, issues, pull requests, and search.

12.4kCode ExecutionUpdated 2 days ago