Recall

MCP文档知识

提供方 未标注

文档知识 stdio · 本地进程 未标注 社区 / 第三方 ClaudeCursorVS CodeCline
查看接入方式

在每个智能体中使用你的 Claude Code 记忆:为 Claude Code 提供 Markdown 自动记忆,并通过 [[wiki-links]] 连接到 Codex、Cursor 或任何 MCP 客户端。无需向量,零依赖。

一句话选型结论

按资料字段整理

Recall 属于文档知识类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude、Cursor、VS Code 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

记忆

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
( sample_dir=$(mktemp -d "${TMPDIR:-/tmp}/recall-demo.XXXXXX") || exit trap 'rm "$sample_dir/review.md" "$sample_dir/checks.md"; rmdir "$sample_dir"' EXIT printf '%s\n' 'Before merging, follow [[checks]].' > "$sample_dir/review.md" printf '%s\n' 'Run the focused test before merging.' > "$sample_dir/checks.md" printf '%s\n' \ '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude、Cursor、VS Code,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Recall当前 未标注 stdio · 本地进程 本地部署 有 2026-11-20
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类文档知识本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-11-20上游最后核验时间

详细介绍

14.7 KB
来自项目仓库与上游目录的原文,未做删改

recall

Your Claude Code memory, in every agent. recall reads and writes the memory Claude Code keeps for each project, so Codex, Cursor or an agent you build yourself can use the same memories, over MCP or from code. Zero dependencies, no vectors, no database: the memories stay plain Markdown files.

Claude Code now remembers things on its own: your corrections, how you like to work, project decisions, where things live. It saves them as Markdown files with [[wiki-links]] under ~/.claude/projects//memory/. That is a good format, but only Claude Code reads it. Switch to another agent and it starts from zero.

recall makes that memory portable. It finds the same directory Claude Code uses (same rules, down to its folder-naming hash), reads every file Claude Code writes, and writes files Claude Code reads back.

Quick start: share it over MCP

Try it with sample notes

Run this in Bash or Zsh with Node.js 18 or newer. It creates two temporary notes, asks the read-only MCP server to recall the review note named in requires, and follows its link to checks.```sh
(
sample_dir=$(mktemp -d "${TMPDIR:-/tmp}/recall-demo.XXXXXX") || exit
trap 'rm "$sample_dir/review.md" "$sample_dir/checks.md"; rmdir "$sample_dir"' EXIT

printf '%s\n' 'Before merging, follow [[checks]].' > "$sample_dir/review.md"
printf '%s\n' 'Run the focused test before merging.' > "$sample_dir/checks.md"

printf '%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"recall-demo","version":"1"}}}' \
'{"jsonrpc":"2.0","method":"notifications/initialized"}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"memory_recall","arguments":{"requires":["review"]}}}' |
npx -y @fainir/recall@0.3.0 --dir "$sample_dir" --read-only
)


In the last JSON response, `result.content[0].text` contains both `Before merging, follow [[checks]].` and `Run the focused test before merging.` The second line comes from the linked note. Use the setup below to connect your own project.

### Connect your project

Point any MCP client at recall and the project's repository. `--read-only` lets the other agent read what Claude Code remembers without changing it; leave it off to let both write.

**Codex**```bash
codex mcp add recall -- npx -y @fainir/recall --claude-code /path/to/your/repo --read-only

Cursor (.cursor/mcp.json in the project, or ~/.cursor/mcp.json)```json
{
"mcpServers": {
"recall": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@fainir/recall", "--claude-code", "/path/to/your/repo", "--read-only"]
}
}
}


**Cline**: in the MCP Servers panel choose Configure, and add the same `recall` entry as for Cursor to `cline_mcp_settings.json`. Or ask Cline to "set up the MCP server from https://github.com/fainir/recall": in a test on 2026-11-01 it read this README, added the entry, started the server and listed its tools.

**Gemini CLI**: `gemini extensions install https://github.com/fainir/recall` (it serves the memory of the folder you start Gemini in).

**Any other MCP client**: run `npx -y @fainir/recall` with the same arguments as a stdio server. Needs Node.js 18+.

The agent then has these tools. Here is a real run against a repository with three memories Claude Code wrote:```text
> memory_list
3 memories in /Users/you/.claude/projects/-Users-you-code-acme-api/memory:
- feedback_testing (feedback) - run the integration suite before saying a change works
- reference_ci (reference) - where CI runs and how to rerun a flaky job
- user_role (user) - backend lead, prefers short answers with the command to run

> memory_recall {"requires": ["feedback_testing"]}
## feedback_testing (feedback) - run the integration suite before saying a change works
Run `npm run test:int` (needs the local Postgres from docker compose), not just `npm test`.
**Why:** the unit tests mock the database; two "done" changes broke prod queries.
**How to apply:** any change under src/db/ or src/queries/. CI details in [[reference_ci]].

## reference_ci (reference) - where CI runs and how to rerun a flaky job
CI is GitHub Actions, workflow `ci.yml`. Rerun a flaky job with `gh run rerun --failed`.

tokens_used: 180

memory_recall followed the [[reference_ci]] link on its own. In testing, a Codex agent given only this server answered a question by calling memory_list and then memory_get.

Tool What it does
memory_list Every memory with its type and one-line description. Optional type filter.
memory_get One memory in full. feedback-testing and feedback_testing both work.
memory_recall The named memories plus the ones they [[link]] to, trimmed to a token budget. Unknown names come back as missing.
memory_due Memories old enough to re-confirm before relying on them.
memory_write Save or replace a memory in Claude Code's format, and add it to the MEMORY.md index. Not offered with --read-only.
memory_delete Delete a memory and its index line. Not offered with --read-only.

recall-mcp options: --claude-code [repo] (the default, using the current directory), --dir for any other memory directory (add --format claude-code to write Claude Code's file format there), --read-only, and --allow-secrets. RECALL_DIR, RECALL_READ_ONLY=1 and RECALL_ALLOW_SECRETS=1 work as environment variables.

Use it from code```bash

npm install @fainir/recall
``````js
import { Recall } from '@fainir/recall';

const memory = Recall.forClaudeCode('/Users/you/code/acme-api');
console.log(memory.dir);

for (const m of await memory.list()) console.log(m.name, '|', m.type, '|', m.description);

const slice = await memory.recall({ requires: ['feedback-testing'] });
console.log(slice.memories.map(m => m.name), slice.tokens_used);

// Save something Claude Code will see in its next session.
await memory.write({
name: 'project_freeze',
type: 'project',
description: 'merge freeze until the 3rd for the mobile release',
body: 'No merges to main until Nov 3. Why: mobile release cut.',
});


Output (before the write):```text
/Users/you/.claude/projects/-Users-you-code-acme-api/memory
feedback_testing | feedback | run the integration suite before saying a change works
reference_ci | reference | where CI runs and how to rerun a flaky job
user_role | user | backend lead, prefers short answers with the command to run
[ 'feedback_testing', 'reference_ci' ] 180

write() produces the file Claude Code itself writes:```markdown

name: project_freeze
description: merge freeze until the 3rd for the mobile release
metadata:
node_type: memory
type: project
modified: 2026-10-27T17:51:14.486Z


No merges to main until Nov 3. Why: mobile release cut.


and adds a line to `MEMORY.md`, the index Claude Code loads at the start of every session, leaving the existing lines alone:```markdown
- [Testing](feedback_testing.md) - run the integration suite before saying a change works
- [CI](reference_ci.md) - where CI runs and how to rerun a flaky job
- [Role](user_role.md) - backend lead, prefers short answers
- [project_freeze](project_freeze.md) - merge freeze until the 3rd for the mobile release

Rewriting an existing memory keeps the fields recall does not own, such as Claude Code's originSessionId.

Where Claude Code keeps the memory

claudeCodeMemoryDir(repo) returns the directory, using Claude Code's rules:

  • The project is the git repository root, so subfolders share one memory, and a worktree uses the memory of its main checkout. Outside git, it is the folder itself.
  • The folder name is the project path with every character other than a-z, A-Z and 0-9 turned into -. Paths longer than 200 characters are cut and given the same hash suffix Claude Code adds.
  • CLAUDE_CONFIG_DIR replaces ~/.claude. CLAUDE_CODE_PROJECT_DIR_NAME (next to CLAUDE_CONFIG_DIR) names the folder. An autoMemoryDirectory setting in the project's .claude/settings.local.json or your ~/.claude/settings.json wins over both.

This was checked against a real ~/.claude/projects folder: the rule reproduced 40 of 41 project folder names, including all three long, hashed ones (the other one belonged to a session that was moved after it started). recall listed and parsed all 194 memory files in it.

API

The package exports the Recall class and claudeCodeMemoryDir(). Every method is async.

Call · Arguments · Returns
Recall.forClaudeCode(repo) · path inside a project; default the current directory · a Recall on Claude Code's memory directory, in claude-code format
new Recall({ dir, format }) · dir: memory directory. format: recall (default) or claude-code · a Recall instance
write({ name, type, description, decay_class, body, extra }) · name: slug (required). type: user \ · feedback \ · project \ · reference (required). description: one line, default ''. decay_class: permanent \ · slow \ · fast \ · ephemeral, default slow. body: Markdown, default ''. extra: more frontmatter fields · { name, type, decay_class, updated_at }. Creates or replaces /.md; in claude-code format also updates MEMORY.md
get(name) · a memory name; - and _ are interchangeable, and a frontmatter name also matches · a Memory, or null
list({ type }) · optional type filter · Memory[], sorted by name
recall({ requires, link_depth, budget_tokens }) · requires: names. link_depth: [[link]] hops to follow, default 1. budget_tokens: default 2000 · { memories: Memory[], tokens_used, missing: string[], dropped: string[] }
dueForReview(asOf) · Date or date string, default now · Memory[] past their review window, each with age_days
delete(name) · exact memory name · true if a file was removed, false if it did not exist
claudeCodeMemoryDir(repo) · path inside a project · the directory path (it may not exist yet)

A Memory is { name, type, description, updated_at, frontmatter, body, links }. type and updated_at come from the flat fields or from Claude Code's metadata: block, whichever the file has. links lists the memory names the body links to, deduplicated and in order.

write, get and delete throw on an unsafe name; write also throws on an invalid type or decay_class, a non-string body or description, or a reserved extra key. recall never throws on unknown names; it lists them in missing.

Memory file format

One file per memory, .md, with frontmatter and a Markdown body. recall reads both shapes, whichever format you pick for writing.

Claude Code's format (format: 'claude-code'; older Claude Code files have a flat type: instead of metadata:, and recall reads those too):```markdown

name: feedback_testing
description: run the integration suite before saying a change works
metadata:
node_type: memory
type: feedback
modified: 2026-10-20T09:12:44.120Z


Run npm run test:int first. CI details in [[reference_ci]].


recall's own format (`format: 'recall'`, the default, which earlier versions wrote):```markdown
---
name: top-customers
type: project
description: paying customers above $10K ACV
decay_class: slow
updated_at: 2026-05-25
---
- Northwind - $48K ACV (see [[northwind-account]])
  • Names: a-z, 0-9, - and _, starting with a letter or digit, up to 128 characters. That keeps file names safe on every OS.
  • Links: [[name]], [[name|label]] and [[name#heading]] all point at name. They are case-insensitive, - and _ match each other, and links inside code are ignored.
  • Frontmatter is a small YAML subset: key: value lines, quoted strings, # comments, and one level of nesting (Claude Code's metadata: block).
  • Other files (MEMORY.md, README.md, My Notes.md, folders) are not memories and are skipped.

How recall() picks the slice

  1. Every name in requires. No embeddings, no fuzzy search.
  2. Every memory reachable through [[wiki-links]] from those, breadth-first, up to link_depth hops.
  3. If the total is over budget_tokens (estimated as characters / 4), memories are dropped until it fits: the deepest links first, so the required memories go last; at the same depth, ephemeral first, then fast, slow, permanent. Their names come back in dropped, and the rest keep their walk order.

For an agent that knows what it needs, explicit keys beat similarity search: asking for "voice" should return the voice memory, not four memories that mention the word.

Decay

decay_class says how often a memory should be re-confirmed. dueForReview() returns the ones whose last update (Claude Code's modified, or recall's updated_at) is older than their window. Nothing is deleted automatically.

decay_class Due for review after
permanent 730 days
slow (default) 90 days
fast 30 days
ephemeral 7 days

Limitations

  • Privacy: serving Claude Code's memory to another agent sends those memories to that agent's model provider. Use --read-only and point it only at projects you are happy to share.
  • Secrets: a memory can capture a credential from a debugging session. Before a memory leaves the server, recall replaces recognisable secrets with [redacted]: passwords in connection URLs, bearer tokens, private key blocks, and Anthropic, OpenAI, GitHub, Slack, AWS, Google and Stripe keys, plus JWTs, and says how many it hid. The files on disk are not changed. --allow-secrets turns this off. It is a safety net for known formats, not a guarantee: keep secrets out of memories.
  • Claude Code reads MEMORY.md at the start of a session, so a memory another agent writes shows up in Claude Code's next session, not the current one. Claude Code loads only the first 200 lines (or 25 KB) of that index.
  • Writes are atomic (temp file + rename), but the last writer wins. There is no locking between recall and a running Claude Code session.
  • Auto memory is per machine. recall does not sync it anywhere.
  • The token count is an estimate (characters / 4), not a tokenizer.

Development

No dependencies, so there is nothing to install:bash git clone https://github.com/fainir/recall.git cd recall npm test # node:test, no network node examples/basic.js # the library on a plain recall directory

License

MIT


More open source by Nir Feinstein

  • agent-harness - make Claude Code or Codex act as a product team, a CEO or a portfolio manager
  • frugal - your agent finds the cheaper honest way before it pays for anything
  • flipback - an automatic /goal for every turn: sends Claude Code back when it stops early
  • most-capable-agent-system-prompt - the copy-paste prompt for a self-improving agent system
  • All projects

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Recall 怎么安装?

在客户端按下面的安装命令接入:( sample_dir=$(mktemp -d "${TMPDIR:-/tmp}/recall-demo.XXXXXX") || exit trap 'rm "$sample_dir/review.md" "$sample_dir/checks.md"; rmdir "$sample_dir"' EXIT printf '%s\n' 'Before merging, follow [[checks]].' > "$sample_dir/review.md" printf '%s\n' 'Run the focused test before merging.' > "$sample_dir/checks.md" printf '%s\n' \ '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion。装完在客户端配置里引用同一个包或端点。

Recall 怎么在 Claude、Cursor、VS Code 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Recall 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Recall 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Recall 支持哪些客户端?

资料标注支持 Claude、Cursor、VS Code、Cline、Gemini CLI、Codex;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Recall 能提供哪些能力?

资料显示能力标签包括 记忆。具体工具清单以官方文档为准。

Recall 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Recall 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-11-20。