loading…
Search for a command to run...
loading…
Exposes identity, tools, workflows, guardrails, and evaluation as MCP tools — so any AI agent can read and write your ecosystem programmatically.
Exposes identity, tools, workflows, guardrails, and evaluation as MCP tools — so any AI agent can read and write your ecosystem programmatically.
Exposes identity, tools, workflows, guardrails, and evaluation as MCP tools — so any AI agent can read and write your ecosystem programmatically.
Setup · Tools · Architecture · Ecosystem
┌─────────────────────────────────────────────┐
│ AI Agent / LLM │
│ (Claude, GPT, Cursor, etc.) │
└──────────────────┬──────────────────────────┘
│ MCP Protocol
┌──────────┴──────────┐
│ aman-mcp │ ← this server
│ 11 tools across │
│ 5 ecosystem layers │
└──┬──┬──┬──┬──┬─────┘
│ │ │ │ │
┌─────┘ │ │ │ └─────┐
▼ ▼ ▼ ▼ ▼
acore akit aflow arules aeval
identity tools flows guards eval
amem (memory) runs as its own MCP server — see amem.
One-liner:
claude mcp add aman -- npx -y @aman_asmuei/aman-mcp
Or manually add to ~/.claude/settings.json:
{
"mcpServers": {
"aman": {
"command": "npx",
"args": ["-y", "@aman_asmuei/aman-mcp"]
}
}
}
Add to .cursor/mcp.json:
{
"mcpServers": {
"aman": {
"command": "npx",
"args": ["-y", "@aman_asmuei/aman-mcp"]
}
}
}
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"aman": {
"command": "npx",
"args": ["-y", "@aman_asmuei/aman-mcp"]
}
}
}
aman-mcp speaks standard Model Context Protocol over stdio:
npx @aman_asmuei/aman-mcp
~/.acore/core.md| Tool | Description |
|---|---|
identity_read |
Read the full core.md identity file |
identity_summary |
Get structured summary: AI name, user name, trust level, personality |
identity_update_session |
Update the Session section (resume, topics, decisions) |
~/.akit/kit.md| Tool | Description |
|---|---|
tools_list |
List all installed tools with status |
tools_search |
Search tool registry by query |
~/.aflow/flow.md| Tool | Description |
|---|---|
workflow_list |
List all defined workflows |
workflow_get |
Get a specific workflow's steps |
~/.arules/rules.md| Tool | Description |
|---|---|
rules_list |
List all rule categories |
rules_check |
Check if an action violates any rules |
~/.aeval/eval.md| Tool | Description |
|---|---|
eval_status |
Get evaluation metrics (sessions, trust, trajectory) |
eval_log |
Log a session with rating and notes |
Discrete arcs of work, LRU-positioned across 10 active slots, peer to intentions / eval / rules. Active project surfaces unconditionally in SessionStart.
Storage: ~/.aprojects/dev/plugin/projects.md (single file via MarkdownFileStorage; matches intentions pattern).
Tools:
project_add — create at #1, shift others, evict at #11project_get — read oneproject_list — filter by status / inActiveListproject_active — fast path: position #1project_load — fuzzy match, restore from off-listproject_touch — bump in-list project to #1project_save — append timestamped session noteproject_close — transition to complete / paused / abandonedproject_update — patch metadata; reciprocally updates intentions.linkedProjectIdLifecycle vs LRU: orthogonal axes. status is lifecycle (active/paused/complete/abandoned). inActiveList is LRU membership. LRU eviction at #11 sets inActiveList=false but keeps status=active — the project is still alive, just not in the top 10.
Bidirectional link: Setting linkedIntentionId on a project also sets linkedProjectId on the intention (and vice versa). Closing one side does NOT close the other.
Override paths root: $AMAN_PROJECTS_HOME (used by tests).
src/
├── index.ts Entry point — server setup, transport
├── tools/ MCP tool definitions per layer
├── parsers/ Markdown file parsers
└── utils/ Shared utilities
The server reads and writes the same files as the CLI tools:
| File | Layer |
|---|---|
~/.acore/core.md |
Identity and personality |
~/.akit/kit.md |
Tool registry |
~/.aflow/flow.md |
Workflow definitions |
~/.arules/rules.md |
Guardrail rules |
~/.aeval/eval.md |
Evaluation log |
git clone https://github.com/amanasmuei/aman-mcp.git
cd aman-mcp
npm install
npm run build
npm run lint
npm test
aman
├── acore → identity → who your AI IS
├── amem → memory → what your AI KNOWS
├── akit → tools → what your AI CAN DO
├── aflow → workflows → HOW your AI works
├── arules → guardrails → what your AI WON'T do
├── aeval → evaluation → how GOOD your AI is
└── aman-mcp → MCP server → the bridge ← YOU ARE HERE
| Layer | Package | What it does |
|---|---|---|
| Identity | acore | Personality, values, relationship memory |
| Memory | amem | Automated knowledge storage (MCP) |
| Tools | akit | 15 portable AI tools (MCP + manual fallback) |
| Workflows | aflow | Reusable AI workflows |
| Guardrails | arules | Safety boundaries and permissions |
| Evaluation | aeval | Relationship tracking and session logging |
| Unified | aman | One command to set up everything |
Contributions welcome! Open an issue or submit a PR.
11 tools. 5 layers. One MCP server.
Run in your terminal:
claude mcp add aman-mcp -- npx Security
Low riskAutomated heuristic from public metadata — not a security guarantee.