Loading…
Search and analyze 85.7M judicial decisions across 90 jurisdictions with citation network analysis and legal risk assessment.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 28 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The legal-mcp MCP server exposes 40 tools, focused primarily on AI capabilities. Its published description reads: "Search and analyze 85.7M judicial decisions across 90 jurisdictions with citation network analysis and legal risk assessment". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates legal-mcp D+ — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check legal-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add legal-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://caselaw.patent-space.dev/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search case law across jurisdiction/topic/keywords/year range.
Search statute texts by jurisdiction and optional filters.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: tool_generate_legal_draft
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: ip_entity_resolve
A tool description tries to alter the model’s use of another tool.
before running ip_entity_profile to verify the correct entity. Accepts any languRecommendationDescriptions must describe only their own tool.
tool: ip_events_snapshot
A tool description tries to alter the model’s use of another tool.
cally to enable ip_events_detect to find changes. Args: source_id: Snapshot sRecommendationDescriptions must describe only their own tool.
tool: tool_generate_strategic_recommendations
A tool description tries to alter the model’s use of another tool.
tput dict (from tool_analyze_party_performance) and applies decision tree logic to generate prRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: tool_analyze_party_performance
An unusually long description is a common injection-padding tactic.
description length 2447 charsRecommendationKeep descriptions concise.
AWS's official fully managed remote server that provides real-time access to comprehensive AWS documentation, API references, troubleshooting guides, and architectural guidance across multiple knowledge sources including What's New posts, Builder Center content, blog posts, and Well-Architected frameworks for building applications, managing infrastructure, and learning AWS services through natural language queries.
Search live events, conference weeks, host cities, venues, and artist tour schedules.
Live verifiable on-chain data for the $BOBAI token on BNB Chain.
Identity certification, public registry, reputation scoring, and x402 micropayments for AI agents built on Base and Solana.
Search 11M+ products across SG, SEA, and US. Agent-native catalog for AI shopping agents.
Generate legal markdown draft for common document types.
Estimate legal risk for a provided situation.
任意の管轄で判例をフルテキスト付きで検索する。 Args: query: 検索クエリ（事案の記述、キーワード、当事者名など） jurisdiction: 管轄（US, GB, EU, JP, AU, CA, DE, FR, IN, BR, KR, etc.） max_results: 最大取得件数 legal_area: 法分野フィルタ（contract, tort, ip, criminal,
複数管轄を横断して判例を検索する。 Args: query: 検索クエリ jurisdictions: 検索対象管轄リスト（デフォルト: ["US", "GB", "EU", "JP", "AU"]） max_results_per_jurisdiction: 各管轄での最大取得件数 Returns: dict: { "results": {<jurisdiction>: [cases...]},
特定の判例のフルテキストと要旨を取得する。 Args: case_id: 判例ID（各管轄固有のID） jurisdiction: 管轄コード Returns: dict: { "case_id": str, "title": str, "full_text": str, "summary": str, "date": str, "court": str, "parties": list[str]
事案の記述から類似判例を検索する。 Args: text: 事案の記述（事実関係、争点、法的問題など） jurisdiction: 管轄（"ALL"で全管轄を検索） max_results: 最大取得件数 Returns: dict: { "similar_cases": [{"case_id": str, "title": str, "relevance": float, "text": str
特定の法分野における判例トレンドを分析する。 Args: legal_area: 法分野（contract, tort, ip, criminal, administrative, etc.） jurisdiction: 管轄コード date_from: 開始日（YYYY-MM-DD形式） date_to: 終了日（YYYY-MM-DD形式） Returns: dict: { "trend_sum
Search IP statistics (patents, trademarks, GII rankings) by jurisdiction and indicator.
Search IP disputes and enforcement data (UDRP/Section337/EPO Opposition/PTAB/Special301/CBP).
Return integrated IP enforcement profile (Special 301 + seizures + Notorious Markets).
Compare IP dispute forum volumes: UDRP vs Section 337 vs EPO Opposition vs PTAB.
List all available IP dispute and enforcement indicators by source.
Extract structured metadata from a judgment / decision / UDRP / opposition text. Workflow: 1. Call with text + hint_source → get partially-extracted JSON schema (dates, case numbers, damages, provisio
Return the empty case metadata schema template. Use this to understand the required JSON structure before filling manually.
Resolve a company/organization name to its canonical form. Returns canonical name, ID, country, known aliases, and confidence score. Useful before running ip_entity_profile to verify the correct entit
Cross-source IP activity profile for a company/organization. Searches available data sources for the entity's IP footprint. Returns: - Resolved canonical entity info - Patent filing activity (PCT, nat
Search the entity registry by name, country, type, or industry. entity_type: "corporation", "npe", "university", "government", "individual" industry: "telecommunications", "semiconductors", "pharmaceu
Detect changes and notable events across all IP data sources. Compares current values against previous snapshots. Args: severity: Filter by "critical", "warning", or "info" (None = all) source_id: Fil
Take a snapshot of current IP statistics for future change detection. Run periodically to enable ip_events_detect to find changes. Args: source_id: Snapshot specific source only (None = all sources) R
View previously detected and recorded IP events. Args: days_back: Look back this many days (default 30) severity: Filter by "critical", "warning", or "info" country_code: Filter by country limit: Max
Generate a cross-border IP enforcement playbook with candidate forums and recommended strategy.
Get IP litigation analytics for specified entities. Returns case counts, win/loss ratio, key counterparties.
Analyze litigation party performance with quality-controlled statistical analysis. Returns standardized analytics output including: - Win rate with Bayesian confidence intervals - Benchmark comparison
Generate priority-ranked strategic recommendations from analytics output. Takes AnalyticsOutput dict (from tool_analyze_party_performance) and applies decision tree logic to generate priority-ranked r
Check whether a case has been overruled, distinguished, or is still good law. Returns a traffic-light signal: - GREEN: No negative treatment found - YELLOW: Distinguished/questioned but not overruled
Get cases that cite a given case, with treatment analysis. Each citing case includes treatment detection: - "neutral": Standard citation - "distinguishing": Case was distinguished or questioned - "ove
Get all cases cited by a given case. Args: case_id: The citing case's ID Returns: dict with cited_cases list and count
Extract legal citations from text using jurisdiction-specific patterns. Supports 12 jurisdictions: US, EU, UK, JP, DE, IN, AU, FR, CA, NZ, KR, BR. Args: text: The legal text to extract citations from
Get current caselaw database statistics. Returns: dict with total_cases, total_citations, and by_jurisdiction breakdown
判事の統計情報を返す: 担当件数、結果分布、法分野、活動期間。 Args: judge_name: 判事名（部分一致検索） jurisdiction: 管轄フィルタ（US, JP, EU, etc.） — 必須 year_from: 開始年フィルタ year_to: 終了年フィルタ Returns: dict: total_cases, outcome_distribution, case_typ
指定トピックについて複数法域の判例を横断比較する。 件数、時期の分布、結果の傾向、裁判所レベルを法域ごとに集計し 横断的な比較分析を返す。 Args: topic: 検索トピック（例: "platform liability", "著作権侵害", "GDPR"） jurisdictions: 比較対象の法域リスト（例: ["US", "EU", "JP", "GB"]） max_results_p
指定判例を中心とした引用ネットワークをグラフ形式で返す。 BFSで引用チェーンを辿り、ノード（判例）とエッジ（引用関係）を返す。 ハブ判例（被引用数が多い）の特定も行う。 未解決の引用（cited_case_id=NULL）もcited_referenceとして返す。 Args: case_id: 起点となる判例ID（例: "US:cl:12345"） depth: 探索深度（1=直接引用のみ、2
Advanced case search with type/subject/date filters. Args: query: Search text (case name, keywords, or party name) jurisdiction: Filter by jurisdiction code (US, EU, JP, IN, etc.) case_type: Filter by
Get importance score and citation network for a specific case. Args: case_id: The case identifier
Get statistics on case classification (types, subjects, outcomes).
Search IP disputes (UDRP, PTAB, EPO opposition, ITC 337, etc.). Args: query: Search text dispute_type: Filter by type (udrp, ptab, epo_opposition, itc337, upc, wipo_adr) jurisdiction: Filter by jurisd
Search statutes and legislation. Args: query: Search text (law name, section number, keywords) jurisdiction: Filter by jurisdiction max_results: Maximum results
Return server health status including DB stats, uptime, and FTS5 index state. Returns: dict: status, total_cases, jurisdictions, citations, fts5_indexed, last_updated, uptime_seconds