RECLUSE Spider MCP Server
Enables a CI gate that blocks pull requests when the 'spider weave' check fails, preventing insecure code from being merged.
Provides a shared pattern database backend using Postgres/Supabase for deduplication, anonymous contribution, and retrieval of verified bug patterns.
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., "@RECLUSE Spider MCP Server check this contract for known bug patterns"
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.
🕸️ RECLUSE
An autonomous detect→fix→verify loop for the bugs that hide in your system's seams. MCP server + GitHub Action + a shared bug-corpus.
The recluse bites the bugs that hide in the seams.
When you vibe-code, writing is fast but debugging is slow — you didn't write the code, so you don't know where it broke. And the bugs that actually bite in production usually aren't in one file; they live in the seams between subsystems: a value written in cents and read as dollars, an auth check that passes on NULL, an RLS policy that leaks every row, a SECURITY DEFINER function anyone can call because the grant went to PUBLIC.
RECLUSE traces those seams (producer → store → consumer), catches the mismatch with live evidence, dispatches a fixer, re-verifies — then pools every caught pattern into a shared corpus so the next project catches the same trap at round-zero.
→ Live page & corpus: https://eduverse-ai.app/recluse
What it does — a closed loop
WEB (detect) → CATCH (contract mismatch) → SPIDER (autonomous fix) → RE-WEAVE (verify) → loop until 🔴 = 0WEB — fan out read-only QC agents with different viewpoints (security, data/payment, integration contracts). One reviewer's blind spot is another's catch.
CATCH — where a producer/consumer contract tears, report it with the exact coordinate (
file:line, constraint, RLS policy) and a severity.SPIDER — dispatch a fixer agent per finding into an isolated git worktree; several fix in parallel without collision. Only the orchestrator merges — detectors stay read-only.
RE-WEAVE — re-run the fixed strand and its neighbors to prove no regression. Loop until clean.
The orchestration (fan-out, dedup, dispatch, re-weave) is deterministic code — a plain loop, not model-driven. Only the spiders (detect/fix) are LLM calls.
What it caught (real, on a live app)
Run against a production Next.js + Supabase/Postgres app, it found privilege-escalation bugs a static review had passed:
a SECURITY DEFINER function callable by anon, because
REVOKE EXECUTE ... FROM anonis a no-op when the grant is to PUBLIC;a plpgsql guard bypassed by NULL three-valued logic —
NULL OR falseis NULL, whichIF NOTtreats as false, so the guard's exception never fired;a SECURITY DEFINER view that let anon write through it, bypassing RLS on the base table.
All three only reproduced against a live endpoint — reading the source called them safe.
Each is now a built-in detection signal (spider_signals) with the exact query to
reproduce it — alongside curriculum order-integrity (band inversion / cyclic
prerequisites), per-user-limit anonymous farming, stream-budget 502s, and
event producer↔consumer contract drift.
Related MCP server: evm-agent-toolkit
Quickstart
① MCP server — for your editor (Claude, Cursor, any MCP client)
One line, no clone — published on npm:
{ "mcpServers": { "recluse": {
"command": "npx",
"args": ["-y", "recluse-mcp"],
"env": { "SPIDER_CORPUS_API": "https://eduverse-ai.app/api/corpus" }
} } }Tools: spider_plan · spider_classify_tier · spider_checklist · spider_signals (detection query/grep per bug class) · spider_record_pattern (local + shared contribution) · spider_pull_corpus (collective pull, verified-first).
Resources: spider://checklist · spider://queries · spider://corpus · spider://blackbox.
Knowledge is built into the server — the checklist, contract queries, and a seed
corpus of live-verified bug classes ship inside the package, so it works standalone. If
you also run the spiderweb-qc skill, its richer
reference files are picked up automatically (set SPIDER_REF_DIR).
② GitHub Action — gate every PR (blocks on 🔴)
# .github/workflows/recluse.yml
name: RECLUSE
on:
pull_request:
branches: [main]
jobs:
weave:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with: { fetch-depth: 0 }
- uses: vinsenzo83/recluse@v1.1
with: { base: origin/${{ github.base_ref }} }
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}Without a key it runs in advisory mode (known-trap checklist, non-blocking). With ANTHROPIC_API_KEY it does a real weave on the diff, blocks on 🔴, and contributes new patterns to the corpus.
Spider tiers — resource by criticality
Not every path deserves Opus. Tier by risk:
Spider | Model | Scope | Verification |
🕷️ King | Opus | payments · auth · GDPR · data loss · secrets | adversarial multi-vote + re-weave |
🕸️ Mid | Sonnet | business logic · contracts · i18n · gating | single + one refute pass |
🐜 Baby | Haiku | docs · dead code · lint | single pass |
So you're not paying Opus rates to check a comment — and the paths where a false negative is expensive get the most scrutiny.
The shared corpus
Every caught bug is distilled into a stack-keyed pattern (detection signal + fix principle) and pooled. A new project checks known traps at round-zero — the more it's used, the thicker the net.
Scrub-first: file paths, code literals, secrets (keys / JWT / high-entropy), emails, URLs, IPs are stripped before anything is shared; anything still suspicious is rejected. Only the generalized technique leaves your machine.
Anonymous: contributors/projects are stored as irreversible hashes — no identity, no raw text.
Consensus: a pattern needs 3 independent contributors before it's marked
verified.
Corpus API (base = SPIDER_CORPUS_API)
POST /patterns{klass,name,signal,fix,tags?,severity?,tier?}→ scrub · dedup · trust accrual (rate-limited per IP)GET /patterns?tags=postgres,payment&class=unit&verified=1&limit=50→ pull the corpus (verified=1= consensus-verified only, for production use)
Contributing is open — pick a contributor token, POST. No signup, no key required (the token is your anonymous identity, not a credential).
Honest limitations
Early (v0.1.1), best-tested on Next.js / Supabase / Postgres — other stacks have thinner coverage until the corpus fills in.
Running it costs tokens. The tool is free to use, but a full weave spawns model calls (Opus on critical paths). It's not free to run.
Not open-source. The MCP client is on npm and the repo is source-available, but not OSI-licensed; the corpus backend is a hosted, closed service. A free tool, not an open one.
"Live evidence only" is the rule, not a proof. The model can still be wrong — the re-verify step is the guard, not a guarantee.
Principles
No fabrication (live evidence only) · scrub-first (zero code/secret leakage) · opt-in & anonymous · detection = read-only, fixes = isolated spiders.
Repo layout
src/index.js # MCP server (stdio)
cli/recluse.mjs # CI weave CLI
action.yml # GitHub ActionThe shared corpus is a hosted service (https://eduverse-ai.app/api/corpus); its backend (schema, scrub pipeline, ingestion) is closed-source.
License
UNLICENSED (proprietary). Free to use; not open-source.
Available Tools
6 toolsspider_checklistA
차원별 전수 체크리스트(증거 없이 PASS 금지)를 반환. 파일 부재 시 내장 체크리스트 + 세션 실증 그물코(권한상승·순서·비용·이벤트) 병합.
Inputs: dimension.
spider_classify_tierA
finding을 King/Mid/Baby 거미로 분류하고 모델·검증표수를 반환. 수정 거미 급파 전 호출. 비용·권한상승·순서무결성 경로 반영.
Inputs: area (required), severity.
spider_planB
대상에 대한 거미줄 검증 계획을 반환: 던질 거미(차원·등급·모델), 우선 점검할 학습 패턴, 절대원칙. 라운드 시작 시 호출.
Inputs: target (required), thorough.
spider_pull_corpusA
공유 corpus(집단 거미 두뇌)에서 검증된 패턴을 가져온다. verified 우선·tag/klass 필터. 원격 미설정/실패 시 내장 corpus로 graceful 폴백. 라운드 시작 시 알려진 함정 우선 점검용.
Inputs: tags, klass, limit, verified.
spider_record_patternB
이번 라운드에 잡은 버그를 학습 corpus에 1줄 패턴으로 증류 추가(다음 라운드에 먼저 점검). 실제로 잡은 것만.
Inputs: fix (required), hit (required), name (required), klass (required), +2 more.
spider_signalsA
실증 버그 클래스의 탐지 신호(라이브 쿼리/grep)와 수정 원칙을 반환. klass/tier/tag로 필터. 계획 후 이 신호를 그대로 실행해 증거를 수집하라.
Inputs: tag, tier, klass.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct step in the spider verification workflow: planning, classification, checklist, signals collection, pattern recording, and corpus retrieval. There is no overlap in functionality.
All tools use the 'spider_' prefix and underscore separators, but some names are verb_noun (e.g., spider_plan, spider_record_pattern) while others are noun-only (e.g., spider_checklist, spider_signals). This minor inconsistency prevents a perfect score.
With 6 tools, the set is well-scoped for a specialized verification server. Each tool earns its place without being redundant or excessive for the domain.
The tools cover the core lifecycle: planning, classification, checklists, signal detection, pattern recording, and corpus access. A minor gap could be a dedicated analysis or reporting tool, but the workflow is largely complete.
Maintenance
Related MCP Connectors
Atomadic MCP: 68 deterministic tools for agent identity, escrow, SLA, EU AI Act compliance.
Free MCP contract auditing for AI agents and developers. Check tool schemas, detect potential breaking changes between versions, and get structured compatibility findings before deployment. Static analysis only.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Self-hosted MCP server: 26 deterministic dev, security, and EVM tools.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables scanning Solidity smart contracts for 13 vulnerability classes using pattern-based analysis; provides full audit, quick scan, gas analysis, and detector catalog through MCP tools.MIT
- AlicenseAqualityDmaintenanceAn MCP server that gives autonomous coding agents deterministic, schema-validated tools for EVM smart contract development — security scanning, gas profiling, compiler diagnostics, and transaction simulation.91MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to record auditable work ledgers with evidence chains, from contract to proof packet, via MCP tools for file scanning, code review, and issue triage.7MIT
- FlicenseNot gradedqualityBmaintenanceEnables Solidity callgraph and control-flow analysis to detect reentrancy vulnerabilities in smart contracts, with MCP integration for automated security auditing and DeFi vulnerability triage.8-