
Aurekai MCP
- Updated May 3, 2026
- aurekai/aurekai-mcp
Aurekai MCP is a MCP server that exposes akai doctor, manifests, artifacts, feature queries, and runtime inspection to your agent.
About
The Aurekai MCP server connects AI coding agents to the Aurekai akai stack through Model Context Protocol stdio transport. Developers who run Aurekai-powered agents install it when they need doctor-style diagnostics, manifest and artifact lookups, feature queries, and runtime inspection from the same session where they edit code. It is aimed at operators and developers already on Aurekai who want fewer context switches than opening separate dashboards or CLI-only flows. Use it during build when integrating Aurekai, and keep it registered in operate when you iterate on live behavior or debug odd runtime states. The package publishes as @aurekai/mcp on npm with server schema version 0.8.0-alpha.3, so expect alpha APIs and verify behavior before relying on it in critical paths. It complements agent skills by offering protocol-level tools rather than prompt recipes.
- akai doctor diagnostics exposed as MCP tools for agent-driven health checks
- Query manifests and artifacts without leaving the coding agent
- Feature-query and runtime inspection for Aurekai-based workflows
- stdio transport via @aurekai/mcp npm package (v0.8.0-alpha.3)
- GitHub source: aurekai/aurekai-mcp for self-hosted stdio wiring
Aurekai MCP by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
claude mcp add aurekai-mcp -- npx -y @aurekai/mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @aurekai/mcp |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | May 3, 2026 |
| Repository | aurekai/aurekai-mcp ↗ |
What it does
Wire Claude Code or Cursor to Aurekai akai doctor, manifests, artifacts, and live runtime checks while you ship agent features.
Who is it for?
Best when you're shipping Aurekai or akai-based agents and want in-editor diagnostics and artifact visibility.
Skip if: Skip if you're not using Aurekai and only need generic log tailing or unrelated cloud monitoring.
What you get
Your agent can run doctor checks, query features, and inspect runtime state through stdio MCP tools aligned with your Aurekai workflow.
- MCP tools for doctor, manifests, artifacts, and feature queries
- Agent-callable runtime inspection without custom glue code
By the numbers
- Server version 0.8.0-alpha.3
- Single npm package @aurekai/mcp with stdio transport
- Repository: github.com/aurekai/aurekai-mcp
README.md
@aurekai/mcp — Aurekai MCP Server
0.8.0-alpha.5 · capability-native · zero dependencies · stdio + Streamable HTTP
Exposes all 9 Aurekai capability families (111 commands) as MCP tools with full protocol-level features:
tool annotations, resource pagination, named prompts, _meta proof propagation, and embedded resource outputs.
Install
npm install -g @aurekai/mcp
Usage
stdio (default — for Claude Desktop, Cursor, etc.)
// claude_desktop_config.json
{
"mcpServers": {
"aurekai": {
"command": "aurekai-mcp"
}
}
}
Streamable HTTP (optional)
AKAI_MCP_HTTP_PORT=3100 aurekai-mcp
# POST JSON-RPC to http://127.0.0.1:3100/mcp
Protocol Surface
| Feature | Status |
|---|---|
tools/list — 89 operators across 9 capability families |
✅ |
Tool annotations (readOnlyHint, destructiveHint, idempotentHint) |
✅ |
resources/list — 13 aurekai:// resource URIs |
✅ |
resources/read — live reads for runtime/capabilities, queue/stats, models |
✅ |
Resource pagination (nextCursor) |
✅ |
| Resource subscriptions (acknowledge) | ✅ |
prompts/list + prompts/get — 8 named capability prompts |
✅ |
_meta proof propagation on tool call results |
✅ |
| Embedded resource outputs for proof-emitting tools | ✅ |
logging server capability |
✅ |
Streamable HTTP transport (AKAI_MCP_HTTP_PORT) |
✅ |
Capability Families
| Family | Operators | Examples |
|---|---|---|
runtime |
11 | akai_api, akai_queue, akai_workflow |
commerce |
11 | akai_gate, akai_pay, akai_ledger |
intake |
12 | akai_transcribe, akai_ingest, akai_segment |
memory |
11 | akai_fpq, akai_fpqx, akai_embed, akai_vec |
proof |
8 | akai_proof, akai_canon, akai_graph, akai_hash |
reason |
5 | akai_reason, akai_physics, akai_flow, akai_learn |
wire |
5 | akai_tel, akai_wire, akai_moq, akai_net |
publish |
9 | akai_brief, akai_narrate, akai_pack, akai_distribute |
substrate |
17 | akai_capability, akai_space, akai_compress |
Named Prompts
| Prompt | Description |
|---|---|
turn-this-call-into-a-deliverable |
audio → transcribe → brief → deliverable |
inspect-this-artifact-lineage |
Resolve full Merkle lineage for an artifact |
build-a-model-memory-pack |
FPQ compress + roundtrip + export memory pack |
compare-these-reasoning-branches |
Dual branch diff with recommendation |
generate-client-invoice-from-usage |
Metering records → invoice |
produce-wire-device-report |
PCAP → SIP event + device report |
run-a-release-gate |
proof validate + manifest verify + SLI auto-run |
make-a-client-brief-from-this-audio |
audio → transcript → structured client brief |
Resources (aurekai:// URIs)
aurekai://runtime/capabilities · aurekai://queue/stats · aurekai://ledger/portfolio
aurekai://models · aurekai://model-memory · aurekai://features/{artifact}
aurekai://proof/{id} · aurekai://graph/{node}/lineage · aurekai://space/{name}
aurekai://wire/{capture_id} · aurekai://project/{id} · aurekai://invoice/{id} · aurekai://cms/{entry_id}
Runtime Requirement
Tools require the akai binary on PATH (from aurekai/native-runtime)
or set AKAI_BIN=/path/to/akai. Without it, tools return a clear error message — no crash.
Registry Targets
- Smithery
- Glama
- Official MCP Registry
- PulseMCP
Recommended MCP Servers
How it compares
MCP integration for the Aurekai runtime, not a standalone agent skill or generic observability SaaS.
FAQ
Who is Aurekai MCP for?
Developers and small teams building on Aurekai who want MCP tools for doctor, manifests, artifacts, and runtime inspection inside their coding agent.
When should I use Aurekai MCP?
Use it when you are debugging Aurekai features, validating manifests or artifacts, or inspecting runtime behavior during build and operate iterations.
How do I add Aurekai MCP to my agent?
Register the stdio server using the @aurekai/mcp npm package in your agent’s MCP config, pointing at the published version and restarting the client.