priornerualnet-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@priornerualnet-mcp validate my prior graph on data.csv, then benchmark it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
priorneuralnet-mcp
Domain-Prior Mask-Constrained Neural Networks for p >> n tabular data, plus an
MCP server so LLM agents can run the whole loop (validate a prior → benchmark →
inspect concept drivers) over structured tools.
A prior graph — an explicit feature → concept mapping (JSON or two-column
CSV), e.g. genes → biological pathways, sensors → physical subsystems — is
compiled into a binary mask. Dense layers are constrained to that mask: every
hidden neuron is a named domain concept, by construction, not by hope.
Mathematical formulation
Let M ∈ {0,1}^{C×F} be the prior mask (C concepts, F features), with
M[c,j] = 1 iff feature j belongs to concept c. A masked layer computes
y = (W ⊙ M) x + b, forward uses only effective weights W_eff = W ⊙ MInitialization scales each row by its own fan-in n_c = Σ_j M[c,j]
(UpperUniform bound √(6/n_c)), not the dense fan-in F — under-scaling
sparse rows is the classic bug this avoids; a unit test pins it.
Gradient hygiene: a grad_fn hook zeroes ∂L/∂W outside the mask, and after
every optimizer step weights are re-projected (W ← W ⊙ M), so AdamW momentum
and weight decay can never leak mass into forbidden connections. Unmapped
(“orphan”) features are not silently dropped: they route through a separate,
small, weight-decayed residual channel — the prior claims they are noise, and
that claim is testable by construction.
The network: x → MaskedPriorLinear → concept activations h (named) → optional residual channel → small MLP head → logits. Baselines built
automatically: a parameter-matched UnconstrainedMLP (width solved so its
active trainable parameter count hits the prior model's budget) and a standard
full-width MLP. Attributions: Integrated Gradients (pure PyTorch, n_steps=32)
with respect to both input features and named concept neurons, giving edge
weights feature → concept and concept → prediction.
The benchmark: stratified K-fold comparison plus a sample-efficiency learning
curve (25% / 50% / 100% of training data), identical training protocol and
identical hyperparameters for every model. The point of the curves is the
low-data regime: with n shrinking, a black box first spends capacity
memorizing noise directions; the prior model's hypothesis class simply does not
contain most of those directions.
Related MCP server: groundtruth-mcp
Install
pip install -e ".[dev]"Python ≥ 3.11. Core: torch, scikit-learn, pandas, pyarrow, pydantic v2, typer,
plotly, jinja2, mcp[cli].
CLI
priorneuralnet validate-graph --data data.csv --prior prior.json --target y
priorneuralnet benchmark --data data.csv --prior prior.json --target y \
--n-splits 5 --epochs 60 --output-dir runs
priorneuralnet generate-demo --output-dir examples/demo_run # synthetic p>>n demo
priorneuralnet inspect-concepts --run-id <id> --concept <name> --top-k 10Every command prints JSON on stdout (agent-friendly). Artifacts per run:
manifest.json (compact, LLM-sized), report.html (Plotly: Sankey
features → concepts → target, generalization-gap and sample-efficiency curves,
concept-importance bars, activation heatmap), model.pt,
concept_activations.parquet.
MCP server
priorneuralnet-mcp # stdio transportRegister with any MCP client:
{"mcpServers": {"priorneuralnet": {"command": "priorneuralnet-mcp"}}}Tools: validate_domain_prior, run_priorneuralnet_benchmark,
inspect_concept_drivers. Resource: priorneuralnet://runs/{run_id}/manifest.
The engine (engine/) never imports mcp; the server is a thin JSON-safe
wrapper — a test enforces this boundary.
Demo
examples/demo_run/ (generated by priorneuralnet generate-demo) contains a
synthetic p >> n dataset: N=240 samples, P=300 features grouped into 15 named
pathways, only 3 of which drive the target through a non-linear mixture; the
ground truth is written next to the data (ground_truth.json) so recovery can
be checked, not assumed.
Tests
pytest -vtest_masked_gradients.py— masked connections keep exactly-zero weights and gradients through AdamW steps; per-row fan-in init; parameter counting.test_prior_graph.py— mapping formats, validation errors, mask/sparsity stats.test_p_gt_n_benchmark.py— end-to-end benchmark; injected true pathways recovered in the top concept attributions; artifact schema.test_mcp_tools.py— tool/resource registration, round-trips, engine-never- imports-MCP boundary.
License
Apache-2.0 (see LICENSE, NOTICE).
Available Tools
3 toolsinspect_concept_driversC
Return a concept's attribution rank plus its top-k feature drivers.
Inputs: run_id (required), concept_name (required), top_k, output_dir.
run_priorneuralnet_benchmarkB
Benchmark the prior-constrained network against parameter-matched MLPs.
Writes artifacts under <output_dir>/<run_id>/ (manifest.json,
report.html, concept_activations.parquet, final_model.pt,
concept_drivers.json) and returns the run id, verdict, per-model val
scores and a pointer to the full manifest.
Inputs: data_path (required), prior_path (required), target_column (required), epochs, +3 more.
validate_domain_priorB
Check a dataset + feature->concept prior and report graph statistics.
Returns {valid: bool, stats: {...}} or {valid: false, error: ...}. Stats include sparsity density, per-concept fan-in and orphan features.
Inputs: data_path (required), prior_path (required), target_column (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools map to distinct workflow stages: validating a prior, running a benchmark, and inspecting a concept's drivers. The only mild overlap is that run_priorneuralnet_benchmark produces concept_drivers.json, which inspect_concept_drivers also surfaces, but targeted inspection remains clearly separate.
All names use snake_case with a leading verb and domain object (validate_domain_prior, run_priorneuralnet_benchmark, inspect_concept_drivers). The pattern is predictable and readable.
Three tools are well-scoped for a focused research server: validate input, execute benchmark, inspect result. No extraneous tools; though minimal, each earns its place.
Core workflow is covered from prior validation through benchmark execution to concept-driver inspection. Minor gaps exist around run management (listing/retrieving prior runs, cleanup) and prior editing, but agents can work around these via returned paths and run ids.
Maintenance
Related MCP Connectors
Stateless agentic tools over MCP: concept extraction, long-context, knowledge graph, planning.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Trusted multi-domain data for AI: 59 tools, MCP Apps, Skills, 520+ cross-domain benchmarks.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables multi-model leader-worker agent orchestration, workflow execution, and deterministic validation via structured MCP tools.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to run project-specific checks, replays, simulations, and queries as MCP tools, providing ground-truth feedback on config edits instead of guessing.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables LLMs to orchestrate AI agents and tasks, inspect DAG workflows, monitor cluster metrics, and perform safe database queries and statements through standardized MCP tools.189Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables MCP-compatible clients to access model registry, prediction logging, drift detection, bias/fairness auditing, compliance and governance queries, explanation generation, LLM/RAG monitoring, content safety, alert management, multi-agent workflow tracking, and performance metrics through 197 tools across 18 domains. Supports stdio and hosted Streamable HTTP transports, plus MCP Apps interactive audit cards.35 PyPIMIT