Finch
io.github.finchagenticPublished by GitHub account finchagenticv4.7.0Updated Oct 24, 2026
Agentic AI runtime: persistent memory, vault, autonomous agents, deep research, DeFi execution.
Overview
Finch is an agentic AI runtime MCP server giving assistants persistent memory, a versioned vault, named agents, workflows and DeFi execution tools.
- What you can do
- Store, search and version knowledge in a memory and vault, with a chronicle of past sessions
- Spawn, recall and update named agents, pulling related memory and vault context
- Run automations, monitors, packets and deep research that auto-saves and links reports
- Save coding and debugging sessions as versioned, project-linked vault entries
- Execute Base and Robinhood Chain DeFi actions and fetch market data, web and GitHub results
- When to use it
- Useful when you want context to survive across chat sessions, or want assistants that keep state, run scheduled research, or act on-chain. It fits research, coding and DeFi workflows that need durable memory rather than one-shot tool calls.
- Requirements
- Runs as a remote endpoint or as a local npm package (Node.js via npx) over stdio; the README recommends pinning the version. Optional account credentials via FINCH_SESSION_TOKEN or FINCH_API_KEY, and one LLM provider key (BANKR_API_KEY, ANTHROPIC_API_KEY, OPENAI_API_KEY or GROK_API_KEY) for ask_finch and deep_research. Optional FIRECRAWL_API_KEY, GITHUB_TOKEN, ALCHEMY_API_KEY and FINCH_WALLET_PASSPHRASE.
Installation
In SourceWeft
- Open Finch in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.finchagentic%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"finch": {
"type": "http",
"url": "https://mcp.finchagentic.com/mcp"
}
}
}README
Finch
The runtime layer for Agentic AI.
Persistent memory, autonomous agents, and workflows that survive every session.
Most AI assistants disappear when the conversation ends. Finch gives them lasting state — memory that accumulates, agents that keep running, vaults that version knowledge, and workflows that continue after you close the chat.
Why Finch
Install
Always pin the version. Never use @latest.
Claude Code
Cursor / Windsurf / Claude Desktop
VS Code
Config file paths
No LLM API key is required to start — 111 of 116 tools are plain reads/writes/on-chain calls that your MCP client's own model already drives; only 5 (ask_finch, deep_research, and scheduled agent learning) do their own multi-step reasoning server-side and need a key (see Configuration). Tools load on first use.
Quick start
Try in your MCP client:
What you get
116 tools across four pillars:
Coding and research sessions persist the same way: deep_research auto-saves its report to vault and links it to related past reports; code_session_save does the same for coding/debugging sessions (vault_save type=code, versioned per project, auto-linked). Both exist so the next session — yours or another agent's — starts with real context instead of cold.
vault_save and agent_spawn also take an optional workspaceProject - the same named Projects a user organizes their Agents/vault content into on the webapp's Agents page. Pass a name and it's matched case-insensitively or created automatically (list_projects to browse what exists first). Hosted vault only - local-vault mode has no project concept.
Default palette is core (lighter context). Full set:
Fully local
Finch is the runtime. Your LLM is the brain. Your data stays yours.
Scheduled/cloud features still need an account. Core memory, vault, and public-data tools work offline of Finch cloud.
Configuration
Cost model: almost everything is free to run — the other 110 tools are plain API/RPC calls, and your MCP client's own model (Claude, GPT, whatever's driving the chat) does all the tool-selection reasoning at no cost to Finch. The 5 exceptions above need their own key because their reasoning happens inside the tool call, invisible to your client, and can't be delegated to it. Set exactly one of the four env vars and every tool that needs it will use it automatically.
Guided setup:
Security
Troubleshooting
Links
MIT License · Finch
Source: README.md at commit 14e0197
Tools
0Version history
1- v4.7.0LatestSep 16, 2026
Score
60% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts