Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.
Persistent knowledge graph and MCP server for AI workflows with git-tracked project context. Exposed over MCP by the kindex mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
It's a persistent knowledge graph for AI-assisted workflows. It indexes your conversations, projects, and intellectual work so that Claude Code, Codex, Gemini CLI, Google Antigravity, OpenCode, Cursor, and other MCP-capable agents never start a session blind. Available as a free MCP plugin or standalone CLI.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Everything the assistant can do here goes through one of these:
payments-refactor — 2 unread (focus: Extract billing service)Extra — Addsmcp — kin-mcp MCP server (for Claude Code, Codex, Gemini, Antigravity, OpenCode, Cursor, etc.)llm — Anthropic-powered extraction (kin learn, kin ask)vectors — sqlite-vec for semantic similarity searchreminders — Natural-language time parsing for kin remindall — Everything aboveTier — Budgetfull — ~4000 tokensabridged — ~1500 tokenssummarized — ~750 tokensexecutive — ~200 tokensYou will need 5 environment variables: CLAUDE_SESSION_ID, CODEX_SESSION_ID, OPENCODE_SESSION_ID, CURSOR_SESSION_ID, KIN_AGENT_ID. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Kindex's toolset — payments-refactor, Extra, mcp and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jmcentire; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| payments-refactor | 2 unread (focus: Extract billing service) |
| Extra | Adds |
| mcp | kin-mcp MCP server (for Claude Code, Codex, Gemini, Antigravity, OpenCode, Cursor, etc.) |
| llm | Anthropic-powered extraction (kin learn, kin ask) |
| vectors | sqlite-vec for semantic similarity search |
| reminders | Natural-language time parsing for kin remind |
| all | Everything above |
| Tier | Budget |
| full | ~4000 tokens |
| abridged | ~1500 tokens |
| summarized | ~750 tokens |
| executive | ~200 tokens |
| index | ~100 tokens |
| Class | Node types |
{ "mcpServers": { "kindex": { "command": "kin-mcp", "args": [] } } }Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| CLAUDE_SESSION_ID | Configuration value read at startup. | Optional |
| CODEX_SESSION_ID | Configuration value read at startup. | Optional |
| OPENCODE_SESSION_ID | Configuration value read at startup. | Optional |
| CURSOR_SESSION_ID | Configuration value read at startup. | Optional |
| KIN_AGENT_ID | Configuration value read at startup. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.