What types of contracts can Spellbook analyze?

Spellbook can analyze a wide range of commercial contracts including NDAs, MSAs, SOWs, employment agreements, vendor agreements, customer contracts, licensing agreements, real estate contracts, and more. The AI is trained on thousands of market precedents and can identify risks, non-standard terms, and missing clauses across all common commercial contract types.

How does the market comparison feature work?

The market comparison feature compares your contract clauses against 2,000+ market precedents to show how your terms compare to market standards. It shows pro-buyer, pro-seller, and market-standard positions for each clause type, helping you understand whether your terms are favorable, aggressive, or in line with market norms.

How do I get a Spellbook API key?

Visit Spellbook.legal and sign up for an account. Navigate to Settings → Integrations or API Settings in your account dashboard to generate an API key. The key gives you access to contract analysis, clause drafting, risk detection, and market comparison features. Contact Spellbook support if you need help setting up API access.

Can Spellbook draft custom clauses for specific jurisdictions?

Yes! When drafting clauses with `draft_spellbook_clause`, you can specify the jurisdiction (e.g. New York, Delaware, California, UK, EU), party position (pro-buyer, pro-seller, neutral), and custom instructions. The AI generates clauses tailored to the specified jurisdiction's legal requirements and your preferred negotiating position.

Spellbook Legal AI MCP Server for CrewAI 13 tools — connect in under 2 minutes

Name: Spellbook Legal AI
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 13 Tools Framework

Connect your CrewAI agents to Spellbook Legal AI through the Vinkius — pass the Edge URL in the `mcps` parameter and every Spellbook Legal AI tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Spellbook Legal AI Specialist",
    goal="Help users interact with Spellbook Legal AI effectively",
    backstory=(
        "You are an expert at leveraging Spellbook Legal AI tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Spellbook Legal AI "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 13 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Spellbook Legal AI MCP Server

Connect to Spellbook Legal AI and bring AI-powered contract drafting, review, and analysis to any AI agent. Trusted by 4,000+ in-house teams and law firms worldwide, Spellbook helps transactional lawyers draft and review contracts faster and more accurately.

When paired with CrewAI, Spellbook Legal AI becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Spellbook Legal AI tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

Contract Analysis — AI-powered review of contracts identifying risks, missing clauses, non-standard terms, and issues
Clause Suggestions — Get AI-generated clause suggestions based on market standards and best practices
Contract Comparison — Compare two contract versions to identify additions, deletions, and modifications
Market Comparison — Compare contract terms against 2,000+ market precedents showing pro-buyer, pro-seller, and market-standard positions
AI Clause Drafting — Generate AI-drafted clauses based on specified requirements, jurisdiction, and party position
Contract Summarization — Generate concise summaries highlighting key terms, obligations, and risks
Risk Assessment — Get comprehensive risk assessments with high, medium, and low risk issues and remediations
Playbook Compliance — Check contracts against company playbooks to identify deviations from standards
Clause Library Search — Search Spellbook's extensive clause library for standard, market-tested clauses
Document Management — Upload, list, and search contract documents with filtering by status and type

The Spellbook Legal AI MCP Server exposes 13 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Spellbook Legal AI to CrewAI via MCP

Follow these steps to integrate the Spellbook Legal AI MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 13 tools from Spellbook Legal AI

Why Use CrewAI with the Spellbook Legal AI MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Spellbook Legal AI through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Spellbook Legal AI + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Spellbook Legal AI MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Spellbook Legal AI for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Spellbook Legal AI, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Spellbook Legal AI tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Spellbook Legal AI against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Spellbook Legal AI MCP Tools for CrewAI (13)

These 13 tools become available when you connect Spellbook Legal AI to CrewAI via MCP:

analyze_spellbook_contract

USE WHEN: - User wants to review a contract for risks - User needs to identify issues in a contract - User asks to "analyze this contract" or "review for risks" PARAMETERS: - document_id (REQUIRED): ID of the document to analyze - analysis_type (OPTIONAL): Type of analysis — "full" (default), "risks_only", "clause_check", "market_comparison" EXAMPLES: - "Analyze document 123 for risks" → call with document_id="123" - "Review this contract for issues" → call with document_id="123", analysis_type="full" - "Check clauses in document 456" → call with document_id="456", analysis_type="clause_check" Analyze a contract document for risks, issues, and suggestions

check_spellbook_playbook

Check contract compliance against a playbook

compare_spellbook_contracts

USE WHEN: - User wants to compare two versions of a contract - User needs to identify changes between drafts - User asks to "compare these contracts" or "show differences" PARAMETERS: - document_id_1 (REQUIRED): ID of the first document - document_id_2 (REQUIRED): ID of the second document - comparison_type (OPTIONAL): Type of comparison — "full" (default), "clauses_only", "risk_comparison" EXAMPLES: - "Compare documents 123 and 456" → call with document_id_1="123", document_id_2="456" - "Show differences between contract versions" → call with document_id_1="123", document_id_2="456", comparison_type="full" Compare two contract versions to identify differences

draft_spellbook_clause

USE WHEN: - User needs to draft a new clause for a contract - User wants AI to generate standard clause language - User asks to "draft a limitation of liability clause" or "write an indemnification clause" PARAMETERS: - clause_type (REQUIRED): Type of clause to draft (e.g. "Limitation of Liability", "Indemnification", "Confidentiality") - party_position (OPTIONAL): Which party position to draft for — "neutral" (default), "pro-buyer", "pro-seller", "pro-vendor" - jurisdiction (OPTIONAL): Jurisdiction for the clause (e.g. "New York", "Delaware", "California", "UK") - custom_instructions (OPTIONAL): Additional instructions or requirements for the clause EXAMPLES: - "Draft a limitation of liability clause" → call with clause_type="Limitation of Liability" - "Draft a pro-buyer indemnification clause for New York" → call with clause_type="Indemnification", party_position="pro-buyer", jurisdiction="New York" - "Write a confidentiality clause with custom instructions" → call with clause_type="Confidentiality", custom_instructions="Include data breach notification requirements" Draft a contract clause using Spellbook AI

get_spellbook_clause_suggestions

Get AI clause suggestions for a contract document

get_spellbook_document

Get detailed information for a specific contract document

get_spellbook_market_comparison

Shows pro-buyer, pro-seller, and market-standard positions. Get market comparison data for a specific clause type

get_spellbook_risk_assessment

Get a detailed risk assessment for a contract document

list_spellbook_documents

Supports filtering by status, document type, and date range. USE WHEN: - User wants to see all their contract documents - User needs to find contracts by status or type - User is exploring their document library - User asks "what contracts do I have" or "list my documents" PARAMETERS: - status (OPTIONAL): Filter by document status (e.g. "Draft", "In Review", "Finalized") - document_type (OPTIONAL): Filter by document type (e.g. "NDA", "MSA", "SOW", "Employment Agreement") - date_from (OPTIONAL): Start date filter (YYYY-MM-DD) - date_to (OPTIONAL): End date filter (YYYY-MM-DD) - page (OPTIONAL): Page number for pagination - page_size (OPTIONAL): Results per page (default: 25, max: 100) EXAMPLES: - "List all my contract documents" → call with no params - "Show contracts in review" → call with status="In Review" - "List NDAs" → call with document_type="NDA" List all contract documents in Spellbook

search_spellbook_clause_library

Search the Spellbook clause library for standard clauses

search_spellbook_documents

Search contract documents by keyword

summarize_spellbook_contract

Generate an AI summary of a contract document

upload_spellbook_document

USE WHEN: - User wants to upload a new contract for review - User needs to analyze a contract received from another party - User asks to "upload this contract" or "analyze this document" PARAMETERS: - file_name (REQUIRED): Name of the document file - file_content (REQUIRED): Base64-encoded file content or document text - document_type (OPTIONAL): Type of document (e.g. "NDA", "MSA", "SOW") EXAMPLES: - "Upload this NDA for review" → call with file_name="NDA.pdf", file_content="[base64 content]", document_type="NDA" - "Analyze this MSA contract" → call with file_name="MSA.docx", file_content="[base64 content]", document_type="MSA" Upload a contract document to Spellbook for analysis

Example Prompts for Spellbook Legal AI in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Spellbook Legal AI immediately.

"Analyze this NDA for risks and issues."

"Draft a pro-buyer limitation of liability clause for Delaware."

"Compare the market standard for indemnification clauses."

Troubleshooting Spellbook Legal AI MCP Server with CrewAI

Common issues when connecting Spellbook Legal AI to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Spellbook Legal AI + CrewAI FAQ

Common questions about integrating Spellbook Legal AI MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.