spark-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
spark-mcp
Creativity and institutional-learning MCP for quant research organizations. Spark remembers what a research organization has tried (including failures), counts every trial so statistical verdicts are deflated rather than lucky, points at unexplored regions of research space, and turns validated trajectories into replay-gated skills. It never backtests and never owns market data — a peer engine computes, Spark judges.
Install
uv venv .venv --python 3.12
uv pip install -e '.[dev]'Requires Python ≥3.11. The [qd] extra needs pyribs (optional).
Related MCP server: metabrain
Quick start
spark init-db # create ~/.spark/spark.db (schema migrations)
spark doctor # capability report (degraded mode, FTS5, sqlite-vec)
spark serve # MCP server over stdio (equivalent: python -m spark_mcp)
python -m pytest -q # test suite incl. the independence gateProgram gates
G1 — judge RED [5,1,1,1,1] single-draw; GREEN only under Tier-3 union-of-5 amendment. The single-draw figure is the original §18.0 criterion result; the GREEN applies only to the amended distribution criterion. See STATUS.md for the phase verdicts and docs/gates.md for the G1–G5 original vs amended/current criteria and evidence refs. Transport decision: docs/adr/transport.md.
Configuration
Copy config.example.yaml to your SPARK_CONFIG path or rely on
defaults (DB at ~/.spark/spark.db). Secrets are environment-variable
references only — never values in files:
Setting | Env var | Purpose |
LLM key |
| scoring / judging calls |
Gateway token |
| skill-promotion manifest POST |
Without an LLM key Spark runs in degraded mode (lexical novelty proxy, deterministic exploration) — fully usable, no network needed.
Use as an MCP server
Any MCP-capable agent or harness can spawn it over stdio:
{ "command": "<venv>/bin/python",
"args": ["-m", "spark_mcp"],
"env": { "SPARK_CONFIG": "/path/to/spark.yaml" } }30 tools, highlights:
Ledger & memory:
register_hypothesis,hypothesis_propose,log_outcome,memory_recall,memory_promote,research_historyExploration:
explore_methods,suggest_next,archive_status,find_analogies,combine_methodsGates & evidence:
significance_gate,check_novelty,backtest_run,causal_check,risk_decomposeSkill evolution:
distill_skill,propose_skill_challenger,run_replay,decide_skill_promotion,approve,retire_skillArtifact evolution:
evolution_run,evolution_status(bounded hypothesis → backtest → DSR-gate → computed-promotion loop; the LLM narrates but never decides; veto post-run viaapprove)Peer seam:
run_summary_ingest(QuantFlow Tier-2 hook),report_write,consolidate,generate_exercise,spark_health,spark_doctor
Artifact evolution
evolution_run evolves research artifacts (hypotheses + backtest specs),
scored by executed provider results through the existing gate stack — trial
governor, DSR significance_gate, strict DSR/SR promotion margins,
challenger/champion/rollback line heads, and human veto. GEPA stays scoped
to skill/procedure text only. Knobs live under research.evolution_* in
config.example.yaml (rounds, margins, first-promotion floor, SOTA-jump
policy, render budget, level-2 spec template + grids). Runs are
bit-reproducible given (seed, caps, provider): reruns agree on decisions
and heads by hypothesis content + episode metrics. Held-out/OOS evidence
never enters evolution feedback — it is promotion-time evidence only
(consolidate also alarms while the replay fixture suite counts below
replay_min_fixtures).
Layout
src/spark_mcp/— package (config, storage, llm protocols+fakes, server, cli, gates, QD archive, skill evolution)tests/— unit tests +tests/independence/(blocking gate: no third-party research repos imported, read, or required at runtime)
Conventions
Time fields are ISO-8601 UTC text; IDs are ULIDs with type prefixes (
hyp_,ep_,trial_,belief_).Storage is SQLite WAL with
PRAGMA user_versionmigrations.Every data-dependent row carries
as_of/data_through; retrieval filters before ranking (no leakage).Trial rows are inserted before dispatch; retries never double-count.
License
MIT — see pyproject.toml.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.
Provenance-first database for teams and agents: every value carries sources, rules and coverage.
Validated trading edges across futures, equities, crypto. Live signals, full audit trail.
Build, backtest, and deploy quantitative trading strategies from your AI agent.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables market-data analysis and quantitative research over a local Parquet lake with tools for bars, indicators, scans, backtests, and safe SQL queries.MIT
- AlicenseNot gradedqualityCmaintenanceProvides a zero-dependency SQLite memory layer for AI agents, letting them record lessons and work state, automatically test recurring patterns as hypotheses, and surface proven preferences during each session.51 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to track ML experiments with a reproducible write contract, internal git snapshots, and a queryable knowledge graph, plus a live web UI for humans.Apache 2.0
- FlicenseBqualityBmaintenanceEnables deterministic, harness-neutral research workflows by unifying research object identity, evidence receipts, claim-evidence graphs, and append-only decision logs, along with specialized scholarly skills for literature analysis, reproducibility audits, and multi-agent review.18660 PyPI1-