Provides access to the EU AI Act as an AI governance framework document, available for listing, retrieval, and phrase search.
Reads AI governance framework documents from the FINOS AI Governance Framework repository hosted on GitHub, enabling listing, retrieval, and phrase search of frameworks, risks, and mitigations.
Provides access to OWASP AI security frameworks, including the OWASP LLM Top 10, OWASP ML Security Top 10, and OWASP Top 10 for Agentic Applications, for listing, retrieval, and phrase search.
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., "@FINOS AI Governance MCP Server search for bias risks in AI governance frameworks"
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.
AI governance framework document access through the Model Context Protocol.
The FINOS AI Governance MCP Server gives an MCP client, such as Claude, VS Code or Cursor, the documents of the FINOS AI Governance Framework: its frameworks, risks and mitigations, read from the framework's repository.
# Clone the repository into aigf-mcp-server
git clone https://github.com/finos/aigf-mcp-server.git aigf-mcp-server
cd aigf-mcp-server
# Python 3.11 or newer is required. Check what python3 is:
python3 --version
# Below 3.11 (the macOS system python3 is 3.9)? Install a newer Python, for
# example `brew install python@3.12` on macOS or the installer from
# https://www.python.org/downloads/, and type python3.12 where python3 is
# written below. On 3.9 the install stops with an error about a dependency
# or setuptools that does not mention the version.
# Install into a virtual environment: a current Python refuses a pip install
# outside one (externally-managed-environment). On Windows, type
# venv\Scripts\ where venv/bin/ is written.
python3 -m venv venv
venv/bin/pip install .
# Check the install. This prints the installed version.
venv/bin/python -c "import finos_mcp; print(finos_mcp.__version__)"You do not start the server yourself: your MCP client starts
venv/bin/finos-mcp when it needs it. The Setup Guide
shows the configuration for Claude Desktop, Claude Code, VS Code and Cursor,
and how to give the server a GitHub token, which is strongly recommended.
Related MCP server: Narad GitHub Agent
Tool | What it does |
| List all available AI governance frameworks from the FINOS repository. |
| Get the complete content of a specific AI governance framework. |
| Find an exact phrase in the text of the AI governance frameworks. |
Tool | What it does |
| List all available AI governance risk documents for threat assessment and security planning. |
| List all available AI governance mitigation strategies for risk reduction and security controls. |
| Get the complete content of a specific AI governance risk document for detailed threat analysis. |
| Get the complete content of a specific AI governance mitigation strategy for risk control implementation. |
Tool | What it does |
| Get real service health status by querying each subsystem. |
| Get cache statistics. |
A client lists the documents, chooses from their names and descriptions, then gets the ones it needs. Parameters, responses and errors for each tool, and that workflow, are in the MCP Tools Reference.
Framework | Description | Focus Area |
NIST AI 600-1 | NIST AI RMF: Generative Artificial Intelligence Profile | Risks particular to generative AI, mapped to the AI RMF |
EU AI Act | European Union Artificial Intelligence Act | AI regulation and compliance in EU |
ISO 42001 | AI Management Systems Standard | AI management and governance |
FFIEC IT Examination Handbook | Federal Financial Institutions Examination Council IT guidance | Financial services IT risk management |
NIST SP 800-53 | Security and Privacy Controls for Information Systems | Cybersecurity controls and privacy |
OWASP LLM Top 10 | Top 10 security vulnerabilities for LLM applications | AI/LLM security risks |
OWASP ML Security Top 10 | Top 10 risks for machine learning systems | ML security and operational risks |
OWASP Top 10 for Agentic Applications | Top 10 risks for agentic AI applications | Autonomous agent security |
Agent Threat Rules (ATR) | Threat rules for AI agent systems | Agent threat modelling |
Canada AI & Financial-Sector Regulatory References | Canadian AI and financial-sector regulatory references | Canadian regulatory compliance |
UK Financial Services AI Regulations | UK financial services AI regulations | UK regulatory compliance |
IOSCO Supervisory Toolkit for AI Use in Capital Markets | Securities-regulator supervisory guidance | Market supervision |
SR 11-7 | US Federal Reserve model risk management guidance | Model risk management |
The framework gives each risk and each mitigation a type in the document's
frontmatter. The labels are the framework's own, from its
site configuration;
the counts were taken on 2026-11-05 and change as the framework grows.
Risk type | Code | Risks |
Operational |
| 11 |
Security |
| 10 |
Regulatory and Compliance |
| 3 |
Mitigation type | Code | Mitigations |
Preventative |
| 17 |
Detective |
| 8 |
The documents are the work of the FINOS AI Governance Framework project, licensed CC BY 4.0; this server does not write them. A risk or mitigation is served as its Markdown body without the front matter; a framework, which upstream keeps as YAML, is rendered as a Markdown document.
Setup Guide: connect your MCP client
MCP Tools Reference: the 9 tools and the list, choose, get workflow
Prompts and Resources Reference: the 3 prompts and the resources, one per document under 3 URI forms
Troubleshooting: common problems and their fixes
Deployment Guide: every setting, running on HTTP, authentication, health checks, upgrading
API Documentation: response schemas, architecture and integration
Development: working on the code and the gates that must pass
Release Process: the version scheme and how a release is cut
See CONTRIBUTING.md for the contribution process, and Development for the development install and the checks a pull request must pass. Every contributor needs a Contributor License Agreement on file with FINOS before a pull request can be merged; EasyCLA checks it on each pull request. Everyone taking part follows the FINOS Code of Conduct.
Questions about the project: help@finos.org
Copyright 2025 FINOS
Software: distributed under the Apache License, Version 2.0 (SPDX-License-Identifier: Apache-2.0)
FINOS Content: the framework documents the server delivers are licensed under CC BY 4.0
Get cache statistics.
Inputs: no named parameters. Returns: Cache statistics.
Get the complete content of a specific AI governance framework.
Use this tool to retrieve detailed framework content for compliance analysis, requirement extraction, or regulatory guidance. The content includes structured requirements, controls, and implementation guidance.
Inputs: framework_id (required). Returns: Framework content with metadata.
Get the complete content of a specific AI governance mitigation strategy for risk control implementation.
Use this tool to retrieve detailed mitigation instructions including security controls, implementation steps, monitoring procedures, and effectiveness measures. Critical for security implementation, compliance remediation, and risk reduction planning.
Inputs: mitigation_id (required). Returns: Document content with metadata.
Get the complete content of a specific AI governance risk document for detailed threat analysis.
Use this tool to retrieve comprehensive risk information including threat descriptions, impact assessments, likelihood analysis, and contextual details. Essential for security assessments, compliance audits, and risk management planning.
Inputs: risk_id (required). Returns: Document content with metadata.
Get real service health status by querying each subsystem.
Inputs: no named parameters. Returns: Service health status.
List all available AI governance frameworks from the FINOS repository.
Use this tool to discover what AI governance frameworks are available for analysis, compliance checking, or reference. This is typically the first step when helping users understand regulatory requirements or compliance gaps.
Examples of available frameworks (call this tool for the full, current list):
NIST AI 600-1 (US federal AI governance)
EU AI Act (European Union AI regulation)
ISO 42001 (international AI management standard)
OWASP LLM Top 10 (AI security best practices)
OWASP ML Security Top 10 (machine learning security best practices)
Each entry is named and described by the document itself, so this reads every document in the catalog rather than only the file listing -- one cached fetch per document. A document that cannot be read keeps a name derived from its filename and has no description, so the listing is always complete.
Inputs: no named parameters. Returns: List of available frameworks.
List all available AI governance mitigation strategies for risk reduction and security controls.
Use this tool to discover security controls, privacy safeguards, and compliance measures for AI systems. Each mitigation document provides actionable controls, implementation guidance, and best practices for reducing identified risks and threats.
Each entry is named and described by the document itself, so this reads every document in the catalog rather than only the file listing -- one cached fetch per document. A document that cannot be read keeps a name derived from its filename and has no description, so the listing is always complete.
Inputs: no named parameters. Returns: List of documents.
List all available AI governance risk documents for threat assessment and security planning.
Use this tool to discover security risks, privacy threats, and compliance vulnerabilities in AI systems. Each risk document provides detailed threat analysis, impact assessment, and contextual information for risk management decisions.
Each entry is named and described by the document itself, so this reads every document in the catalog rather than only the file listing -- one cached fetch per document. A document that cannot be read keeps a name derived from its filename and has no description, so the listing is always complete.
Inputs: no named parameters. Returns: List of documents.
Find an exact phrase in the text of the AI governance frameworks.
Frameworks only: this tool does not search risks or mitigations. To find a risk or a mitigation, call list_risks or list_mitigations, choose from the titles and descriptions, then read it with get_risk or get_mitigation.
The query is matched as one phrase of whole words. Case is ignored, and hyphens and underscores count as spaces, so "third party" finds "third-party". Words of the query that appear apart are not a match, and neither is a word inside a longer one. Link addresses are not searched.
Returns one result per framework that says the phrase, in the order list_frameworks gives them. Results are not ranked. Each has the framework's document_id (pass it to get_framework), the section and passage around the first occurrence, and occurrences, the number of times that framework says the phrase. If nothing is found, no framework says that phrase: try a shorter phrase or a single word.
A search that could not run is an error, not an empty result. A framework that cannot be read is left out, and the search fails if none can be read.
Inputs: query (required), limit. Returns: Search results collection.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 9 tools
The list/get pairs are cleanly separated by resource type (frameworks, risks, mitigations), and search_frameworks is explicitly scoped to frameworks only, so an agent can tell it apart from the getters. The only soft overlap is between get_service_health and get_cache_stats, both diagnostic calls whose boundaries are not fully explained.
Every tool follows the same snake_case verb_noun pattern (list_*, get_*, search_*), with no camelCase or bare-noun outliers. The verb predicts the behavior reliably: list returns catalogs, get returns full document content, search returns matches.
Nine tools is well within the ideal range and each earns its place: three resource types times a list/get pair, plus one search and two small operational diagnostics. Nothing appears redundant or padded.
The read-only document lifecycle is fully covered for all three resources (list + get), plus search for frameworks. The notable gap is that phrase search exists only for frameworks, leaving risks and mitigations requiring an expensive list-then-get flow; there is also no cross-corpus search or framework-vs-requirement comparison capability.
Cited, standards-aware compliance overlay for AI assistants (ISO, NIST, FedRAMP, IRAP), over MCP.
Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.
Ask your own documents and get answers that cite the source passage. Workspace knowledge bases over MCP for Cursor, Claude and any MCP client.
Give your AI agent persistent, governed memory for every project. At task start it recalls the approved decisions, conventions, risks and architecture (semantic search, ranked by importance); at close it proposes what was learned as typed memories that you review and approve — governance, not a notes dump. Agents propose, humans govern: edits go back to pending and deletion is human-only by design. Connect Claude Code, Cursor, Claude Desktop or any MCP client in two minutes with just your API key — hosted (nothing to install) or locally via `uvx solucortex-mcp`. Built by SoluAI and dogfooded daily: SoluCortex is developed using its own living memory.
