mcp server
Code Context Engine
Index your codebase. AI searches instead of re-reading files. 94% token savings.
Description as published by the maintainer. Source
- version 0.4.13
- active
- retrieval
active — Most recent push to the repository was 2026-08-02. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 393 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-02 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 14 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 0.4.13 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-05-03 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-05-03 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub |
Where to get it
Related, by what their authors tagged them
-
io.github.BigJai/tokennuke
— last commit 2026-03-02, shares code-indexing, token-savings
Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.
-
io.github.Alejandro-M-P/git-courer
— last commit 2026-07-31, shares gemini-cli, token-savings
Full git MCP server for LLM agents — 17 tools, AST annotator, auto-backups, real plumbing.
-
datoon
— last commit 2026-08-03, shares token-savings
Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.
-
io.github.CSCSoftware/aidex
— last commit 2026-08-05, shares ai-coding, code-indexing, copilot
Persistent code indexing for AI assistants. 50x less context than grep. 11 languages.
-
io.github.codegraph-ai/codegraph
— last commit 2026-07-19, shares ai-coding, code-indexing, copilot
Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.
-
io.github.BigJai/codemunch-pro
— last commit 2026-03-02, shares code-indexing
Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.
-
Memorix
— last commit 2026-08-06, shares ai-coding, copilot, gemini-cli
Local-first persistent project memory for AI coding agents across MCP clients and sessions.
-
Rails AI Context
— last commit 2026-08-01, shares ai-coding, copilot
38 MCP tools give AI agents live Rails schema, routes, models, and conventions.
-
com.llm-bus/llm-bus
— last commit 2026-06-22, shares ai-coding, multi-agent
Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.
-
io.github.asklokesh/loki-mode
— last commit 2026-08-06, shares multi-agent, openai-codex
Autonomous spec-to-product coding-agent CLI with an MCP server exposing 34 tools over stdio.
These share tags the maintainers applied themselves, such as code-indexing, token-savings, gemini-cli, ai-coding. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: ai-coding, claude, claude-code, code-indexing, codex, copilot, cursor, gemini-cli, github-copilot, llm-tools, mcp-server, multi-agent, open-source, openai-codex, save-tokens, token-savings.
Bring your own setup
We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.
Join ZBS AI Practice Lab