
Finch
io.github.finchagentic由 GitHub 账号 finchagentic 发布v4.7.0更新于 Oct 24, 2026
Agentic AI runtime: persistent memory, vault, autonomous agents, deep research, DeFi execution.
概览
Finch 是一个智能体 AI 运行时 MCP 服务器,为助手提供持久记忆、版本化知识库、命名智能体、工作流和 DeFi 执行工具。
- 可以做什么
- 在记忆与知识库中存储、全文检索并版本化知识,并保留历史记录
- 创建、召回和更新命名智能体,并关联其目标相关的记忆与知识库内容
- 运行自动化、监控、数据包和深度研究,报告自动保存并关联既往研究
- 将编码与调试会话保存为按项目版本化的知识库条目
- 执行 Base 与 Robinhood Chain 的 DeFi 操作,并获取行情、网页与 GitHub 结果
- 适用场景
- 适合希望上下文跨会话保留,或需要智能体保持状态、执行定时研究、进行链上操作的场景。适用于需要持久记忆而非一次性工具调用的研究、编码和 DeFi 工作流。
- 运行要求
- 可作为远程端点,或以本地 npm 包(通过 npx 运行,需 Node.js)以 stdio 方式运行;README 建议固定版本。可选账户凭据 FINCH_SESSION_TOKEN 或 FINCH_API_KEY;ask_finch 与 deep_research 需一个 LLM 提供商密钥(BANKR_API_KEY、ANTHROPIC_API_KEY、OPENAI_API_KEY 或 GROK_API_KEY)。可选 FIRECRAWL_API_KEY、GITHUB_TOKEN、ALCHEMY_API_KEY 与 FINCH_WALLET_PASSPHRASE。
安装
在 SourceWeft 中
- 打开 控制台中的 Finch,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
交给智能体安装
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.github.finchagentic%2Fmcp/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。其他 MCP 客户端
把它添加到你客户端的 mcpServers 配置中。
{
"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
来源:README.md,提交 14e0197
工具
0版本历史
1- v4.7.0最新Sep 16, 2026
评分
已满足适用检查项的 60%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通必需25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式必需10 分
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分