agent-graph-mcp

Run 9 agents at once. MCP server for graph-orchestrated LLM workflows — dispatch up to 16 LLM nodes in parallel fan-out with typed joins, checkpoint/resume, human-in-the-loop approvals, and HMAC-authenticated execution receipts. 25 typed tools.

Expose the ri-agent-graph runtime engine over MCP. Compile declarative JSON workflow specs, execute synchronously or asynchronously, checkpoint/resume, request human approval, capture source witnesses, and get cryptographic receipts — all through 25 typed MCP tools. Normal execution is synchronous. Durable approval is supported only as a SQLite-backed decision.

Quick start

npx (recommended)

npx -y @recursiveintell/agent-graph-mcp --direct --base-url http://127.0.0.1:11434 --model glm-5.2:cloud

Cargo install

cargo install agent-graph-mcp --locked
agent-graph-mcp --direct --base-url http://127.0.0.1:11434 --model glm-5.2:cloud

Daemon mode (production)

agent-graph-mcpd --data-dir ~/.local/share/agent-graph --socket /tmp/agent-graph.sock &
agent-graph-mcp --socket /tmp/agent-graph.sock

Client configs

Hermes Agent:

mcp_servers:
  agent_graph:
    command: agent-graph-mcp
    args: [--socket, /tmp/agent-graph.sock]

Claude Desktop:

{"mcpServers": {"agent-graph": {"command": "npx", "args": ["-y", "@recursiveintell/agent-graph-mcp", "--direct", "--base-url", "http://127.0.0.1:11434", "--model", "glm-5.2:cloud"]}}}

9 agents at once

Fan out to 9 LLM nodes in parallel, then join results into one synthesis:

{
  "name": "9-agent-research-sweep",
  "entry": "fanout",
  "nodes": [
    {"id": "fanout", "type": "passthrough"},
    {"id": "agent_0", "type": "llm", "prompt": "Research topic A: {input}"},
    {"id": "agent_1", "type": "llm", "prompt": "Research topic B: {input}"},
    {"id": "agent_2", "type": "llm", "prompt": "Research topic C: {input}"},
    {"id": "agent_3", "type": "llm", "prompt": "Analyze dimension 1: {input}"},
    {"id": "agent_4", "type": "llm", "prompt": "Analyze dimension 2: {input}"},
    {"id": "agent_5", "type": "llm", "prompt": "Analyze dimension 3: {input}"},
    {"id": "agent_6", "type": "llm", "prompt": "Critique from angle X: {input}"},
    {"id": "agent_7", "type": "llm", "prompt": "Critique from angle Y: {input}"},
    {"id": "agent_8", "type": "llm", "prompt": "Synthesize findings: {collected}"},
    {"id": "join", "type": "join", "config": {"inputs": ["agent_0","agent_1","agent_2","agent_3","agent_4","agent_5","agent_6","agent_7","agent_8"], "output": "collected", "mode": "collect_array"}},
    {"id": "report", "type": "llm", "prompt": "Produce final report from: {collected}"}
  ],
  "edges": [
    {"from": "fanout", "to": "agent_0"}, {"from": "fanout", "to": "agent_1"},
    {"from": "fanout", "to": "agent_2"}, {"from": "fanout", "to": "agent_3"},
    {"from": "fanout", "to": "agent_4"}, {"from": "fanout", "to": "agent_5"},
    {"from": "fanout", "to": "agent_6"}, {"from": "fanout", "to": "agent_7"},
    {"from": "fanout", "to": "agent_8"},
    {"from": "agent_0", "to": "join"}, {"from": "agent_1", "to": "join"},
    {"from": "agent_2", "to": "join"}, {"from": "agent_3", "to": "join"},
    {"from": "agent_4", "to": "join"}, {"from": "agent_5", "to": "join"},
    {"from": "agent_6", "to": "join"}, {"from": "agent_7", "to": "join"},
    {"from": "agent_8", "to": "join"},
    {"from": "join", "to": "report"}, {"from": "report", "to": "END"}
  ],
  "max_parallelism": 9
}

All 9 LLM calls execute concurrently via Tokio JoinSet. The join node collects results, then the report node synthesizes. Scale up to 16 branches per parallel node.

Architecture

MCP Client ──→ agent-graph-mcp (proxy) ──Unix socket──→ agent-graph-mcpd (daemon) ──→ SQLite
               stdin/stdout                 framed              Tokio async I/O

Tools (25)

Graph lifecycle (4): graph_create, graph_list, graph_inspect, graph_render Execution (5): graph_execute, graph_run_start, graph_run_wait, graph_run_cancel, graph_run_get State & checkpoint (4): graph_run_state, graph_run_events, graph_run_checkpoint, graph_run_resume HITL approval (3): graph_approval_list, graph_approval_get, graph_approval_request Evidence (2): graph_source_witness_capture, graph_source_witness_get Templates (4): graph_template_list, graph_template_instantiate, graph_template_candidates, graph_template_outcomes Receipts & status (3): graph_policy_check, graph_run_receipt, graph_status

Built-in templates

Ecosystem

Verification

# Smoke test — 25 tools
echo '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' | \
  npx -y @recursiveintell/agent-graph-mcp --direct --base-url http://127.0.0.1:11434 --model glm-5.2:cloud 2>/dev/null | \
  python3 -c "import sys,json; msg=json.loads(sys.stdin.read()); print(f'{len(msg[\"result\"][\"tools\"])} tools')"

# Build + test
cargo build --release
cargo test --lib --test daemon_recovery --test mcp_integration

License

MIT © RecursiveIntell