Y
Yacine-ai-tech/AgentKit
Governed MCP server and agent runtime: signed action approvals, typed tool effects and audit logs for Claude Desktop, Cursor and custom agents.
SECURITY.md ✓
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
- Copy the command above
- Paste it as one entry under
mcpServersinclaude_desktop_config.json— local servers take command + args (example: clients) - Restart your client
Client config (built from the install command this repo gives)
{
"mcpServers": {
"yacine-ai-tech-agentkit": {
"command": "uvx",
"args": ["agentkit-mcp"]
}
}
}Parsed from the README we fetched on 2026-10-26; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"yacine-ai-tech-agentkit": {
"command": "uvx",
"args": ["agentkit-mcp"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio yacine-ai-tech-agentkit -- uvx agentkit-mcp
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 0 ★ · Yacine-ai-tech/AgentKit · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- collected from the punkpeye/awesome-mcp-servers list · type: MCP server
- Harvest history
- first seen 2026-10-23 · last seen 2026-11-14 · seen 26× · listed by 23 sources
- Score
- score 2,300 · 23 sources · mcp
- Install
uvx agentkit-mcp
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
uvx agentkit-mcp. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
Yacine-ai-tech/AgentKit；first catalogued 2026-10-23；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# AgentKit — A Governed MCP Tool Server
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
An MCP server where tools are declarative, effects are typed, and every action is
policy-gated and audited. It works with any MCP client (Claude Desktop, Cursor,
LangGraph, Claude Agent SDK, CrewAI).
Live Application: agentkit.ysiddo-ai-projects.app.
Research Background: RESEARCH.md / Online Research Documentation
Empirical Benchmarks: BENCHMARK.md / Online Benchmark Dashboard
User Guide: Online User Guide
Self-Hosting Guide: SELFHOSTING.md
Three things distinguish it from a typical MCP server:
Declarative tools. Define tools in YAML over your own Postgres or HTTP API, with no
Python and no fork. (docs/REUSE.md)
Typed effects. Each tool declares an effect (read, write or destructive), and
tools that mutate data do mutate it.
Guardrails that do not depend on the prompt. Writes are off by default, destructive
actions need a human-held approval token the model never sees, every mutating tool
supports dry-run, and every call (allowed and denied) is audited.
(SECURITY.md)
The bundled business-intelligence tools below are the reference pack. They show the
mechanics end to end; they are not the limit of what the server can serve.
## What It Does
Reference BI pack (built in):
6 core MCP tools: querykpis, getcompanyhealth, detectkpianomalies, forecastmetric, listavailablemetrics, getexecutivesummary — plus any tools loaded from declarative YAML packs (packs/), so the real tool count at runtime is 6 or more, not a fixed number. The bundled annotations pack adds 3 more (listannotations, annotatemetric, retractannotation) demonstrating a guarded write/destructive path — see below.
10 MCP resources: kpi://{domain}/latest for each of this project's real seeded domains — Finance, People, Operations, Customer, Engineering, Growth, Logistics, ESG, IT, Security (src/agentkitmcp/data/seed.py).
1 reusable prompt: monthlyexecutivebriefing
> The domain list, tool-pack set, and resource/prompt registration are all derived from the
> same data this server serves (src/agentkitmcp/data/seed.py, packs/.yaml), not
> hardcoded, so adding a domain or tool pack extends this list automatically. You can also add
> your own @mcp.resource / @mcp.prompt decorators. See
> docs/REUSE.md.
Write and destructive actions. The annotations pack lets an agent record a durable
note on a metric (annotatemetric, effect write) and soft-delete one it got wrong
(retractannotation, effect destructive, which requires a human-held
AGENTKITAPPROVALTOKEN the model never sees). Both are off by default
(AGENTKITALLOWWRITES=false). See SECURITY.md
and RESEARCH.md section 2 for the policy-engine model.
Platform capabilities:
Declarative tool packs — add tools over your own Postgres/HTTP in YAML (packs/)
Typed effects + policy engine — GET /api/policy publishes the capability envelope
Audit trail — GET /api/audit, allowed and denied, with deny reasons
Multi-provider LLM routing incl. self-hosted — GET /api/llm-routing
LangGraph 3-agent workflow in workflow.py (Planner → Analyst → Reporter)
Claude Agent SDK demo in demos/claudeagentsdkdemo.py
CrewAI demo in demos/crewaidemo.py
DSPy research scaffold in research/dspyexperiment.py
90+ tests across smoke, API, integration, MCP protocol, policy guardrails, and LangGraph workflow
policy-gated and audited. It works with any MCP client (Claude Desktop, Cursor,
LangGraph, Claude Agent SDK, CrewAI).
Live Application: agentkit.ysiddo-ai-projects.app.
Research Background: RESEARCH.md / Online Research Documentation
Empirical Benchmarks: BENCHMARK.md / Online Benchmark Dashboard
User Guide: Online User Guide
Self-Hosting Guide: SELFHOSTING.md
Three things distinguish it from a typical MCP server:
Declarative tools. Define tools in YAML over your own Postgres or HTTP API, with no
Python and no fork. (docs/REUSE.md)
Typed effects. Each tool declares an effect (read, write or destructive), and
tools that mutate data do mutate it.
Guardrails that do not depend on the prompt. Writes are off by default, destructive
actions need a human-held approval token the model never sees, every mutating tool
supports dry-run, and every call (allowed and denied) is audited.
(SECURITY.md)
The bundled business-intelligence tools below are the reference pack. They show the
mechanics end to end; they are not the limit of what the server can serve.
## What It Does
Reference BI pack (built in):
6 core MCP tools: querykpis, getcompanyhealth, detectkpianomalies, forecastmetric, listavailablemetrics, getexecutivesummary — plus any tools loaded from declarative YAML packs (packs/), so the real tool count at runtime is 6 or more, not a fixed number. The bundled annotations pack adds 3 more (listannotations, annotatemetric, retractannotation) demonstrating a guarded write/destructive path — see below.
10 MCP resources: kpi://{domain}/latest for each of this project's real seeded domains — Finance, People, Operations, Customer, Engineering, Growth, Logistics, ESG, IT, Security (src/agentkitmcp/data/seed.py).
1 reusable prompt: monthlyexecutivebriefing
> The domain list, tool-pack set, and resource/prompt registration are all derived from the
> same data this server serves (src/agentkitmcp/data/seed.py, packs/.yaml), not
> hardcoded, so adding a domain or tool pack extends this list automatically. You can also add
> your own @mcp.resource / @mcp.prompt decorators. See
> docs/REUSE.md.
Write and destructive actions. The annotations pack lets an agent record a durable
note on a metric (annotatemetric, effect write) and soft-delete one it got wrong
(retractannotation, effect destructive, which requires a human-held
AGENTKITAPPROVALTOKEN the model never sees). Both are off by default
(AGENTKITALLOWWRITES=false). See SECURITY.md
and RESEARCH.md section 2 for the policy-engine model.
Platform capabilities:
Declarative tool packs — add tools over your own Postgres/HTTP in YAML (packs/)
Typed effects + policy engine — GET /api/policy publishes the capability envelope
Audit trail — GET /api/audit, allowed and denied, with deny reasons
Multi-provider LLM routing incl. self-hosted — GET /api/llm-routing
LangGraph 3-agent workflow in workflow.py (Planner → Analyst → Reporter)
Claude Agent SDK demo in demos/claudeagentsdkdemo.py
CrewAI demo in demos/crewaidemo.py
DSPy research scaffold in research/dspyexperiment.py
90+ tests across smoke, API, integration, MCP protocol, policy guardrails, and LangGraph workflow
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/yacine-ai-tech-agentkit/)
- Source
- awesome · https://github.com/Yacine-ai-tech/AgentKit
- Browse by field
- MCP servers
- Listed by
- 23 independent sources
- added
- today
- Security policy
- the repository has
SECURITY.mdat its root (we checked that the file exists, not what it says)
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.