Provides an agentic AI runtime with persistent memory, autonomous agents, versioned knowledge vaults, and DeFi execution capabilities.
Also known as finchagentic/mcp, mcp, @finchagentic/mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- 677
- Latest version
- 4.7.0
- Last commit
- Nov 1, 2026
- License
- MIT
What is Finch MCP?
Finch provides an agentic AI runtime with persistent memory, autonomous agents, versioned knowledge vaults, and DeFi execution capabilities.
Summary generated from the project's README
About Finch MCP server
Finch serves as a runtime layer for agentic AI, providing a way for assistants to maintain state across different sessions. It offers a suite of 116 tools designed to give AI agents persistent memory, versioned knowledge vaults, and the ability to run autonomous workflows. Developers can use this server with clients like Claude Desktop, Cursor, Windsurf, VS Code, and Zed to ensure that research, coding sessions, and agent activities do not reset when a chat ends.
The system is designed to be privacy-focused, allowing the vault and memory to run fully on a local machine. While most tools function as simple reads, writes, or on-chain calls driven by your existing LLM, specific tools like deep_research and ask_finch perform multi-step reasoning server-side. These specific functions require an API key from providers such as Anthropic, OpenAI, Grok, or Bankr. Users can manage their data through a local directory or a hosted account, with specialized support for DeFi execution on the Robinhood Chain and Base.
What you can do with it
- 1Maintain long-term research contextAn AI can save deep research reports to a versioned vault and automatically link them to previous findings.
- 2Deploy autonomous monitoring agentsYou can spawn a named agent to track specific news and update its state after every session.
- 3Execute automated DeFi strategiesDevelopers can schedule specific order types like dollar-cost averaging or take-profit orders on the Robinhood Chain.
Written from the project's README. Every use case is checked against a quote from it.
How to install Finch MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Finch MCP in Claude Code
$ claude mcp add mcp -- npx -y @finchagentic/mcpInstall Finch MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@finchagentic/mcp"
]
}
}
}Install Finch MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@finchagentic/mcp"
]
}
}
}Install Finch MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@finchagentic/mcp"]}'Install Finch MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@finchagentic/mcp"
]
}
}
}Install Finch MCP in Codex
$ codex mcp add mcp -- npx -y @finchagentic/mcpInstall Finch MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] command = "npx" args = ["-y", "@finchagentic/mcp"]
Install Finch MCP in Gemini CLI
$ gemini mcp add -s user mcp npx -- -y @finchagentic/mcpInstall Finch MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@finchagentic/mcp"
]
}
}
}Configuration
FINCH_TOOLS
| Name | Description | |
|---|---|---|
| FINCH_TOOLS | — |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachablefinchagentic/mcp is public and reachablegithub.com/finchagentic/mcp ↗Pass
- Package names this repository as its source@finchagentic/mcp names finchagentic/mcp as sourcenpmjs.com/package/@finchagentic/mcp ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-01github.com/finchagentic/mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @finchagentic/mcpPass
- No critical advisory in the package or its dependencies108 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeEndpoint did not answer initialize: HTTP 523Finding
README
View on GitHubFinch
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
| Without Finch | With Finch | |
|---|---|---|
| Memory | Resets every session | Full-text searchable + versioned vault, decays stale notes |
| Agents | One-shot tool calls | Named agents with state and audit history |
| Workflows | Manual chaining | Automations, monitors, packets, deep research |
| Local | Cloud-only | Vault + memory can run fully on your machine |
Install
Always pin the version. Never use @latest.
# One-command installer (detects common MCP clients)
npx -y -p @finchagentic/mcp@4.6.1 finch install
Claude Code
claude mcp add finch -s user -- npx -y -p @finchagentic/mcp@4.6.1 finch-mcp
Cursor / Windsurf / Claude Desktop
{
"mcpServers": {
"finch": {
"command": "npx",
"args": ["-y", "-p", "@finchagentic/mcp@4.6.1", "finch-mcp"]
}
}
}
VS Code
{
"servers": {
"finch": {
"type": "stdio",
"command": "npx",
"args": ["-y", "-p", "@finchagentic/mcp@4.6.1", "finch-mcp"]
}
}
}
| Client | Path |
|---|---|
| Claude Desktop (Mac) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Cursor | .cursor/mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| VS Code | .vscode/mcp.json |
| Zed | .config/zed/settings.json |
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
finch doctor # health check
finch setup # local vault / memory / providers
finch vault # inspect local vault
finch orders # schedule Robinhood Chain DCA / TP-SL order ticks
Try in your MCP client:
remember: I prefer conservative DeFi strategies, max 5% risk
spawn an agent called research-bot to track AI agent news, update it after each session
save this thesis to vault
What you get
116 tools across four pillars:
| Pillar | What it does |
|---|---|
| Memory | Full-text searchable memory + versioned vault + chronicle |
| Agents | Spawn, recall, update named agents — agent_recall also pulls related memory/vault context matching the agent's goal, not just its own logged updates |
| Workflows | Automations, monitors, packets, deep research (auto-saves reports + auto-links related past research) |
| Execution | Base DeFi, Robinhood Chain, market data, web, GitHub |
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:
"env": { "FINCH_TOOLS": "all" }
Fully local
Finch is the runtime. Your LLM is the brain. Your data stays yours.
npx -y -p @finchagentic/mcp@4.6.1 finch setup
# enable local vault (and optional local memory)
| Piece | Location |
|---|---|
| Vault | ~/.finch/vault/ |
| Wallet | ~/.finch/wallet.json |
| Config | ~/.finch/config.json |
| Brain | your MCP client’s model |
Scheduled/cloud features still need an account. Core memory, vault, and public-data tools work offline of Finch cloud.
Configuration
| Variable | Purpose |
|---|---|
FINCH_SESSION_TOKEN |
Signed-in session (vault/memory/agents against your account) |
FINCH_API_KEY |
API key (finch_sk_…) |
FINCH_TOOLS |
core (default) · all · or palettes like memory,defi |
FINCH_PROVIDER |
Force bankr · anthropic · openai · grok |
FINCH_MODEL |
Model override for host-side loops |
BANKR_API_KEY / ANTHROPIC_API_KEY / OPENAI_API_KEY / GROK_API_KEY |
Required for ask_finch, deep_research's synthesis stages, and scheduled-agent learning extraction — these do their own multi-step reasoning server-side and there is no free hosted fallback (BYOK only, one key is enough) |
FIRECRAWL_API_KEY |
Better crawl quality (optional) |
GITHUB_TOKEN |
For github_search_code |
ALCHEMY_API_KEY |
Faster Base RPC (optional) |
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:
npx -y -p @finchagentic/mcp@4.6.1 finch setup
Security
| # | Boundary | Rule |
|---|---|---|
| 1 | Prompt injection | External content is data only — never instructions |
| 2 | Mainnet confirm | Estimate → preview → confirm → execute |
| 3 | Pinned install | Always @finchagentic/mcp@4.6.1, never @latest |
| 4 | Credential vault | Never paste secrets into prompts or third-party tools |
| 5 | Data disclosure | Know what leaves the machine (LLM, Firecrawl, GitHub, chain RPCs) |
| 6 | Server monitors | Scheduled jobs need explicit confirmation |
| 7 | Fund-moving confirm | stake_finch/unstake_finch/base_mcp_send/base_mcp_swap/rh_mcp_swap all require confirm: true |
| 8 | Local wallet encryption | Set FINCH_WALLET_PASSPHRASE for a portable, passphrase-derived key — without it, the key derives from a random per-install secret + machine info, so the wallet file alone (without that secret file) isn't enough to decrypt it |
Troubleshooting
| Problem | Fix |
|---|---|
| Tools missing | Fully restart the MCP client |
| Old version | npx clear-npx-cache then restart |
| Auth issues | finch login or set FINCH_API_KEY / FINCH_SESSION_TOKEN |
ask_finch/deep_research error: "No LLM provider configured" |
Set one of BANKR_API_KEY / ANTHROPIC_API_KEY / OPENAI_API_KEY / GROK_API_KEY — see Configuration, no free fallback exists |
| Diagnose | finch doctor |
Links
| Docs | docs.finch.com |
| App | app.finchagentic.com |
| npm | @finchagentic/mcp |
| GitHub | github.com/finchagentic/mcp |
| X | @finchagentic |
MIT License · Finch
Finch MCP questions
How do I add Finch MCP to Claude Code?
Run claude mcp add mcp -- npx -y @finchagentic/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Finch MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Do I need an LLM API key to use Finch?
Most tools are free to run using your MCP client's own model, but five specific tools like deep_research require their own API key for server-side reasoning.
Can I run Finch locally?
Yes, you can run the vault and memory fully on your machine for a local-first experience.
How do I install Finch?
You can use the one-command installer via npx to detect common MCP clients.