Contextful

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 CodeWindsurf
查看接入方式

为代理型AI提供高效上下文管理:MCP代码搜索、证据包、图上下文及大型项目记忆功能。

一句话选型结论

按资料字段整理

Contextful 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
npx @inferensys/contextful init --workspace . npx @inferensys/contextful search "where is user auth handled" --workspace . --budget 2000

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
Contextful当前 未标注 stdio · 本地进程 本地部署 有 未标注
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
最近核验未标注上游最后核验时间

详细介绍

6.2 KB
来自项目仓库与上游目录的原文,未做删改

Contextful

⚠️ This is in early alpha. The API, features, and integrations are not stable. Expect breaking changes. Feedback & contributions are very welcome!

Local Context Management + Search Engine + Memory for Agentic AI.

Contextful is a runtime contextual layer and local search engine for agents that gives them one fast way to find, compress, cite, and remember project context.

Available as a CLI-first tool with an MCP runtime bridge and generated agent instructions, it integrates seamlessly with Codex, Claude Code, Cursor, Windsurf, GitHub Copilot, VS Code, Cline, Roo Code, Continue, and Zed.

Instead of making an agent read 40 files every session, Contextful indexes the project once and returns a ranked, cited, token-budgeted context pack.

Why?

Context has always been a bottleneck for agentic AI. Large context window models (for example, 1M tokens) are:
1. Expensive and require significantly more compute & processing time.
2. More likely to lose key information as the context window fills up.
3. Most projects have millions of lines of code, but agents can only fit in limited tokens per context window.

The current solution is to make the agent guess which files to read, then pay the token cost to read them every session. This is slow, expensive, and lossy.

Apart from this, agents have no way to store or share learnings across sessions. Every time they start, they forget everything and have to re-read the same context again.

I started developing Contextful to keep the context window smaller by enabling efficient knowledge retrieval. If we index the project and return a ranked, cited, token-budgeted context pack, we can:
- 100x more efficient token usage: stop paying tokens to re-read the same files.
- Fewer tool calls: one context pack can replace dozens of grep, glob, and read-file calls.
- No lost context between sessions: agents can store session learnings in an evidence-backed memory ledger.
- Shareable project knowledge: lessons and context packs survive context compaction and future sessions.

Key Features

1. Context Management

The default local store is SQLite with FTS-backed search and typed graph tables. V1 ships with:

  • SQLite as the default local store.
  • FTS5 lexical/BM25 search.
  • Typed graph tables: nodes, edges, node_props, edge_props.
  • A hot adjacency cache for common graph relations.
  • Deterministic structural fingerprints inspired by Code2Vec-style secondary reranking signals.

The next storage upgrades are optional semantic vectors through sqlite-vec, LanceDB, or local HNSW, and compressed adjacency lists with Roaring bitmaps or CSR arrays for larger repositories.

2. Search Engine

Contextful analyzes the query, classifies intent, and combines lexical search, symbols, docs, graph relationships, and memory hits to retrieve the right evidence. The goal is Google-level project search for agents: vague queries like "resources for auth onboarding" should still land on the right code, docs, and prior lessons.

3. Memory Ledger

Agents can store lessons, decisions, and useful project facts, but not as loose "remember this" notes. Every memory requires evidence refs from files, symbols, commits, or prior context packs. When the evidence changes, Contextful marks the memory stale.

4. Contextful Execution

Contextful is an MCP server, local indexer, and small CLI:

  • MCP server: the agent interface.
  • Local daemon / watcher: indexing, rebuilds, freshness, and future benchmarks.
  • CLI (cxf): human setup, indexing, search, memory writes, and local smoke tests.

MCP is the right interface because tools, resources, and prompts are exactly what MCP standardizes. The agent asks for context; Contextful returns compact evidence.

Install```bash

npx @inferensys/contextful init --workspace .
npx @inferensys/contextful search "where is user auth handled" --workspace . --budget 2000


Run as an MCP server:```bash
npx @inferensys/contextful server

CLI

The primary binary is cxf; contextful is also provided as a readable alias.```bash
cxf init --workspace <path>
cxf index --workspace <path> [--watch]
cxf daemon --workspace <path>
cxf search "<query>" --workspace <path> --budget 2000 --json
cxf memory add --workspace <path> --claim <text> --evidence <ref>
cxf server


## Core MCP Tools

Keep the agent surface small:

- `context_pack(query, budget, scope)` - the killer tool. Returns a ranked, cited, token-budgeted bundle instead of forcing 40 random file reads.
- `search_code(query, mode, filters)` - powerful code, docs, symbol, and memory search.
- `trace_path(from, to, edge_types)` - graph traversal across files, symbols, modules, and config.
- `impact_analysis(symbol_or_file)` - reverse dependencies and likely tests.
- `why_changed(symbol_or_file)` - current evidence plus git history.
- `recall_memory(query, scope)` - search session learnings and durable project lessons.
- `write_lesson(claim, evidence_refs, scope)` - store an evidence-backed memory.

## MCP Client Setup

Use this stdio server command in any MCP-aware coding tool:```json
{
  &quot;mcpServers&quot;: {
    &quot;contextful&quot;: {
      &quot;command&quot;: &quot;npx&quot;,
      &quot;args&quot;: [&quot;-y&quot;, &quot;@inferensys/contextful&quot;, &quot;server&quot;]
    }
  }
}

Codex:```bash
codex mcp add contextful -- npx -y @inferensys/contextful server


## CLI-First Agent Flow

Use `cxf init` once per workspace. It indexes the project and writes `.contextful/AGENT_INSTRUCTIONS.md`, a compact skill-style guide that tells agents when to call `context_pack`, when to search more narrowly, and when memory writes are allowed.

Use `cxf search` when a human wants to test the same evidence pack an agent will receive:```bash
cxf search &quot;how does auth load user profiles?&quot; --workspace . --budget 2000

The MCP server remains the agent interface. The CLI is for setup, inspection, and repeatable local tests.

Privacy

V1 is local-only. It does not call external embedding APIs, upload source code, edit source files, auto-fix code, or install dependencies inside the target workspace.

Evidence Refs

Memory writes require evidence references returned by search or context packs:

  • file:src/auth.ts:10-40
  • symbol:src/auth.ts#AuthService:12
  • pack:ctx_...

Invalid or stale evidence is rejected or marked stale.

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
Contextful 怎么安装?

在客户端按下面的安装命令接入:npx @inferensys/contextful init --workspace . npx @inferensys/contextful search "where is user auth handled" --workspace . --budget 2000。装完在客户端配置里引用同一个包或端点。

Contextful 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。

Contextful 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。

Contextful 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。

Contextful 支持哪些客户端?

资料标注支持 Claude、Cursor、VS Code、Windsurf、Cline、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。

Contextful 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。

Contextful 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。

Contextful 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 未标注。