13 MCP tools · Rust · Domain-agnostic

m1nd

Spreading activation, noise cancellation, and Hebbian learning over knowledge graphs.

Give your agents a nervous system.

m1nd session

$ m1nd.activate --query "authentication flow"

Activating from 3 seed nodes...
Wavefront: 3 → 12 → 41 nodes across 3 hops

0.92 file::src/auth/middleware.rs (structural: 0.95, semantic: 0.88)
0.87 file::src/auth/jwt.rs (structural: 0.82, semantic: 0.91)
0.81 file::src/session/manager.rs (structural: 0.79, temporal: 0.83)
0.64 file::src/middleware/cors.rs (causal: 0.71)
0.23 file::src/auth/rate_limit.rs structural hole detected

XLR noise cancelled: 8 false-positive edges removed
41 nodes activated in 2.3ms

The problem

LLM agents are powerful reasoners but poor navigators.

They can analyze code, write solutions, and debug problems. But they can't see the shape of what they're working on.

"What does this change affect?"

Blast radius is invisible without structural analysis.

m1nd.impact

"What am I missing?"

Structural holes are undetectable by keyword search.

m1nd.missing

"What else will change?"

Co-change patterns require historical context.

m1nd.predict

"How are these connected?"

Dependency chains span files, modules, and abstraction layers.

m1nd.why

How it works

The core loop

m1nd doesn't search your data -- it activates it. Query a concept, and the graph lights up.

Ingest

Build property graph from source data. Code, JSON, any domain.

Activate

Spreading activation across 4 dimensions with XLR noise cancellation.

Learn

Hebbian plasticity: correct results strengthen connections, wrong results weaken them.

Persist

Graph + plasticity state saved to disk. Next session starts where this one left off.

Four activation dimensions

Structural

Graph topology: edges, PageRank, community structure. How things are wired.

Semantic

Label similarity: char n-grams, co-occurrence (PPMI), synonym expansion.

Temporal

Time dynamics: recency decay, change velocity, co-change history.

Causal

Dependency flow: directed causation along import, call, and contain edges.

13 MCP tools

Everything an agent needs.

Callable by any LLM agent via JSON-RPC stdio. No SDK required.

Discovery

m1nd.activate

Spreading activation query -- "what's related to X?"

m1nd.why

Path explanation -- "how are A and B connected?"

m1nd.missing

Structural hole detection -- "what's missing from this picture?"

m1nd.fingerprint

Equivalence detection -- "are these two things duplicates?"

m1nd.resonate

Harmonic analysis -- standing waves, resonant frequencies, sympathetic pairs.

Change Analysis

m1nd.impact

Blast radius -- "what does changing X affect?"

m1nd.predict

Co-change prediction -- "what else will need to change?"

m1nd.counterfactual

Removal simulation -- "what breaks if we remove X?"

Learning

m1nd.learn

Hebbian feedback -- "this result was correct / wrong / partial."

m1nd.drift

Weight drift analysis -- "what changed since last session?"

m1nd.warmup

Context priming -- "prepare for task X."

System

m1nd.ingest

Load data into the graph. Code extractor or JSON descriptor.

m1nd.health

Diagnostics -- node/edge counts, sessions, persistence status.

Real output

A full session, start to finish.

m1nd ingesting and analyzing its own codebase. Every number is real.

m1nd self-analysis session

1. Ingest > m1nd.ingest path=./
Scanned 32 source files across 3 crates
693 nodes, 2007 edges built in 84ms
Co-change history: 47 commit groups analyzed

2. Activate > m1nd.activate query="spreading activation"
Seeds: activation.rs, graph.rs, xlr.rs
Wavefront: 3 → 18 → 47 nodes
0.94 fn::propagate_wavefront (structural 0.97)
0.91 fn::score_candidates (semantic 0.93)
0.87 fn::xlr_gate (causal 0.89)
0.72 fn::compute_pagerank (structural 0.78)
XLR cancelled 12 noise edges

3. Impact > m1nd.impact targets=["graph.rs"]
Blast radius: 23 nodes across 4 hops
Direct: activation.rs, xlr.rs, temporal.rs, builder.rs
Indirect: server.rs, tools.rs, session.rs
High-impact: graph.rs is a keystone (PageRank top 3%)

4. Missing > m1nd.missing context=["auth", "session"]
Structural hole: no rate_limiter connected to auth module
Weak bridge: session ↔ middleware (single edge, weight 0.3)
2 gaps detected in neighborhood of 34 nodes

5. Learn > m1nd.learn feedback=correct nodes=[activation.rs, xlr.rs]
LTP applied: 14 edges strengthened (avg +0.12)
Plasticity state persisted

6. Counterfactual > m1nd.counterfactual remove=["graph.rs"]
CASCADE: 31 nodes lose connectivity
ORPHANED: 8 functions become unreachable
RESILIENT: temporal.rs, domain.rs survive via alternate paths
Simulation complete: graph.rs is load-bearing

Get started

Up and running in 60 seconds.

Build

cargo build --release

Run

m1nd starts as a JSON-RPC stdio server. MCP-compatible out of the box.

./target/release/m1nd-mcp

Ingest & Query

Send MCP messages over stdin. State persists automatically.

              // Ingest a codebase

              {"method":"tools/call","params":{"name":"m1nd.ingest",

                "arguments":{"path":"/your/project","agent_id":"my-agent"}}}

              // Query

              {"method":"tools/call","params":{"name":"m1nd.activate",

                "arguments":{"query":"authentication","agent_id":"my-agent"}}}

              // Learn from results

              {"method":"tools/call","params":{"name":"m1nd.learn",

                "arguments":{"feedback":"correct","node_ids":["file::src/auth.rs"]}}}

Any domain

Not just code. Ingest any knowledge graph from JSON.

              // JSON descriptor -- works for any domain

              {"nodes": [

                {"id":"concept::activation", "label":"Spreading Activation", "type":"Concept"},

                {"id":"concept::plasticity", "label":"Hebbian Plasticity", "type":"Process"}

              ],

              "edges": [

                {"source":"concept::activation", "target":"concept::plasticity",

                 "relation":"enables", "weight":0.8}

              ]}