Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Autonomous MCP Agent OS: multi-graph memory, Tasks, Skills, A2A, attestation, OpenTelemetry.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
作者没有在注册中心列出安装信息。请查看下方作者的 README。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 ANAMIZED 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.5.0)于3个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
YodMCP is a production-oriented Agent Operating System kernel on MCP: multi-graph memory, Tasks, Skills, A2A, attestation (software / simulated TEE), OpenTelemetry, and plan-based monetization.
This README is written so a senior engineer with only this file + the source tree can install, deploy every surface, exercise features, and verify end-to-end.
FOUNDRY (host-owned trust and memory for long-horizon agent swarms) separates untrusted proposal generation from host-owned verification + established-facts registry.
YodMCP is that registry in production: agents call memory_write; promotion to semantic memory is gated; the host owns the evaluator. Full note: docs/FOUNDRY.md.
Meters first. Seat if the loop holds.
| Unit | Stripe | x402 |
|---|---|---|
| OpenGOS Search $0.40 | Buy | GET /v1/search |
| OpenGOS Draft $2.50 | Buy | GET /v1/draft |
| Agentic OS Cycle $0.75 | Buy | GET /v1/cycle |
| YodMCP Pro $49/mo | Subscribe | USDC |
x402 rail: x402-cloudflare-starter. Desk sync: https://anamized.grok.me
| Surface | Command | Default | Purpose |
|---|---|---|---|
| MCP | yodmcp | stdio | Local MCP clients (Cursor, Claude Desktop, etc.) |
| MCP HTTP | yodmcp --http --port 8000 | :8000/mcp | Remote / Streamable HTTP MCP |
| API | yodmcp-api --port 8080 | :8080 | REST health, memory, audit, skills, billing |
| A2A | yodmcp-a2a --port 9000 | :9000 | Agent Card, message, tasks |
| SDK | from yodmcp.sdk import YodClient | HTTP client | Thin client for the API |
| Skills | skills:// + skills/*/SKILL.md | auto-loaded | Agent Skills as MCP resources |
| Verify | pytest + scripts/verify_e2e.py | CI | Substrate + durable + TEE modes |
git clone https://github.com/ANAMIZED/YodMCP.git
cd YodMCP python -m venv .venv && source .venv/bin/activate # recommended pip install -e ".[dev]"
Copy environment defaults:
cp .env.example .env
| Variable | Default | Meaning | |||
|---|---|---|---|---|---|
YODMCP_MEMORY_BACKEND | memory | memory \ | sqlite \ | durable | |
YODMCP_MEMORY_DB | ./data/yodmcp_memory.db | SQLite path when durable | |||
YODMCP_ATTEST_MODE | software | software \ | simulated_tee \ | nitro \ | sgx |
YODMCP_PLAN | free | free \ | pro \ | enterprise | |
YODMCP_TENANT_ID | default | Soft quota tenant key | |||
YODMCP_SKILLS_DIR | *(auto)* | Override skills root | |||
STRIPE_SECRET_KEY | unset | Enables live Checkout Sessions |
TEE honesty:
nitro/sgxare provider hooks; without real TEE libraries they fall back to simulated claims. Prefersoftwareorsimulated_teefor local verify.
# 1) MCP over stdio (attach from an MCP client)
yodmcp
yodmcp-api --port 8080
yodmcp-a2a --port 9000
Cursor — project .cursor/mcp.json or global MCP settings:
{
"mcpServers": { "yodmcp": { "command": "yodmcp", "args": [], "env": { "YODMCP_MEMORY_BACKEND": "memory", "YODMCP_PLAN": "free", "YODMCP_ATTEST_MODE": "software" } } } }
If yodmcp is not on PATH, use the module form:
{
"mcpServers": { "yodmcp": { "command": "python", "args": ["-m", "yodmcp"], "cwd": "/absolute/path/to/YodMCP", "env": { "PYTHONPATH": "src", "YODMCP_MEMORY_BACKEND": "memory" } } } }
Claude Desktop — same shape under mcpServers in claude_desktop_config.json.
Streamable HTTP MCP (remote clients that support URL transport):
yodmcp --http --host 0.0.0.0 --port 8000
docker compose up --build
Single API container:
docker build -t yodmcp .
docker run --rm -p 8080:8080 -e YODMCP_PLAN=free yodmcp
# Unit + integration
YODMCP_MEMORY_BACKEND=memory YODMCP_ATTEST_MODE=software \ PYTHONPATH=src pytest tests/ -v
YODMCP_MEMORY_BACKEND=sqlite YODMCP_MEMORY_DB=/tmp/yodmcp.db \ YODMCP_ATTEST_MODE=simulated_tee \ PYTHONPATH=src pytest tests/ -v
PYTHONPATH=src python scripts/verify_e2e.py
Expected: all tests green; script prints ALL E2E CHECKS PASSED.
API smoke (with yodmcp-api running):
curl -s http://127.0.0.1:8080/health
curl -s http://127.0.0.1:8080/api/skills curl -s http://127.0.0.1:8080/api/billing/plans curl -s http://127.0.0.1:8080/api/billing/status
SDK:
python examples/sdk_quickstart.py # requires API on :8080
| Tool | Description |
|---|---|
memory_write | Insert one memory node (facts/decisions). Not for plans (plan_cache_put). |
memory_read | Retrieve nodes by similarity or item_id. Not for plans (plan_cache_get). |
memory_delete | Hard-delete one node + incident edges. Idempotent if missing. |
memory_consolidate | Promote importance ≥ 0.8 into semantic summaries. Does not delete sources. |
memory_stats | Node/edge/entity counts. Not content (memory_read). |
tasks_create | Create a durable pending task handle. |
tasks_get | Fetch one handle by id. |
tasks_list | List recent handles, optional status filter. |
tasks_update | Patch status/progress/result. Not cancel (tasks_cancel). |
tasks_cancel | Mark a handle cancelled (kernel state only). |
tasks_stats | Counts by status. Not a listing (tasks_list). |
skills_list | List Agent Skills + skills:// URIs (bodies are resources). |
a2a_card | A2A Agent Card JSON. Not the MCP catalog (discover_capabilities). |
plan_cache_get / plan_cache_put / plan_cache_delete | Semantic plan templates. Not memory facts. |
cache_stats | In-process cache entry/hit totals. |
attestation_recent | TRACE-style provenance claims. Not the audit trail (audit_recent). |
audit_recent | Policy/tool Decision-System-of-Record events. |
discover_capabilities | List MCP tools + loaded skills. |
echo | Liveness probe (message echoed + version). |
Resources:
skills://{name} — skill markdown bodyyodmcp://agent-card — agent card JSONBuilt-in skills are always registered. Disk skills under skills/*/SKILL.md are loaded automatically (override via YODMCP_SKILLS_DIR). Repo ships:
memory-hygiene, safe-tool-use, funding-usdc, repo-bootstraplong-horizon-planning| Plan | $/mo | Tool calls/day | Durable | TEE |
|---|---|---|---|---|
| Free | 0 | 500 | — | — |
| Pro | 49 | 50k | yes | simulated |
| Enterprise | 499 | unlimited | yes | Nitro/SGX hooks |
STRIPE_SECRET_KEY is set; otherwise checkout returns status: payment_link| Option | Link |
|---|---|
| YodMCP Pro | https://buy.stripe.com/bJe3cw0kCaLrbVz1AY43S09 |
| YodMCP Enterprise | https://buy.stripe.com/9B68wQ1oGcTz9NrfrO43S0a |
| Agentic OS Kernel Support ($99) | https://buy.stripe.com/bJecN63wObPv6Bf7Zm43S02 |
| Public Goods Support ($25) | https://donate.stripe.com/00w5kE3wOg5L8Jn2F243S00 |
| Agentic Systems Consulting Hour ($199) | https://buy.stripe.com/dRmaEYgjA9Hnf7LdjG43S0b |
| Network | Address |
|---|---|
| Base | 0xD3d0E9eDAe3Ac7bb199a8EAA761BdA423b878438 |
| Ethereum | 0xD3d0E9eDAe3Ac7bb199a8EAA761BdA423b878438 |
| Solana | ETQwWf19axArsY493UfC6bxe2BmEzmzvCb58PPnC38A |
Canonical: funding/addresses.json
src/yodmcp/ # package (src-layout)
core/ # server, substrate, context memory/ # in-memory + durable SQLite multi-graph tools/ # MCP tool registration + gate tasks/ skills/ cache/ security/ observability/ monetization/ api/ a2a/ sdk/ skills/*/SKILL.md # portable Agent Skills (loaded at runtime) scripts/verify_e2e.py tests/ docs/ARCHITECTURE.md docs/FOUNDRY.md docs/TDQS.md
src/yodmcp/frontend/dashboard.py still uses legacy core.runtime and is not the primary control plane — use yodmcp-api + MCP tools.sqlite backend + shared volume for multi-process durability.Apache-2.0 · CONTRIBUTING · CHANGELOG · ARCHITECTURE · FOUNDRY · TDQS · AGENTS.md