ayunis-legal-mcp

Provides an MCP server (FastMCP) and supporting FastAPI “Store API” for importing, storing (PostgreSQL + pgvector), and semantic-searching German legal texts (scraped/parsed from gesetze-im-internet.de). Includes a CLI for importing/querying and an MCP tool set for AI assistants to search and retrieve legal sections.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp fastapi postgresql pgvector semantic-search rag legal-tech cli docker python
⚙ Agent Friendliness
49
/ 100
Can an agent use this?
🔒 Security
36
/ 100
Is it safe for agents?
⚡ Reliability
20
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
70
Error Messages
0
Auth Simplicity
25
Rate Limits
10

🔒 Security

TLS Enforcement
40
Auth Strength
20
Scope Granularity
10
Dep. Hygiene
50
Secret Handling
70

README indicates TLS for outbound Ollama is configurable via OLLAMA_BASE_URL, but does not state HTTPS/TLS requirements for the exposed Store API/MCP server. Authentication/authorization for inbound APIs is not described. Secrets are referenced via environment variables (good), but secret handling/logging behavior is not evidenced. No dependency/SBOM/CVE posture is provided.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
20
Error Recovery
30
AF Security Reliability

Best When

You control the deployment (Docker), embedding endpoint (Ollama), and are building an assistant workflow that benefits from MCP tools plus a vector-backed search backend.

Avoid When

You need turnkey managed service, standardized SLAs, or you cannot provide/secure an Ollama endpoint and credentials; also avoid if you require documented pagination/idempotency semantics for safe retries.

Use Cases

  • Semantic search over German legal texts by natural language
  • Retrieving specific legal sections/sub-sections (e.g., by § and sub-section)
  • Building RAG/legal research assistants via MCP tools
  • Automating ingestion of legal codes from gesetze-im-internet.de into a vector store
  • Programmatic access via REST for importing, querying, and searching

Not For

  • Production use without hardening/operational safeguards (auth/rate limits/observability)
  • Environments where scraping of external sites is not allowed or cannot be scheduled/managed
  • Use cases that require strict legal compliance/auditing of source text versions beyond what is documented
  • Scenarios needing fine-grained access control per user/tenant (not described)

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: No auth described for Store API or MCP server in provided README OLLAMA_AUTH_TOKEN for calling Ollama embeddings (outbound to embedding provider)
OAuth: No Scopes: No

Authentication/authorization for the exposed Store API (port 8000) and MCP server (port 8001) is not described. Outbound Ollama auth token is mentioned for embeddings.

Pricing

Free tier: No
Requires CC: No

Self-hosted OSS; costs depend on your infrastructure and embedding compute (Ollama).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Semantic search depends on embeddings; failures can occur if Ollama model output dimensionality does not match the fixed 2560-vector schema.
  • Rate limits and retry backoff guidance are not documented; agents may retry aggressively and cause load.
  • Auth/authorization for the exposed APIs is not described; running publicly could be risky.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for ayunis-legal-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered