Skip to main content
Glama
Brinkv3

consulting-mcp-server

by Brinkv3
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Local

Consulting MCP Server

MCP server that exposes three AI pipelines — RAG Pipeline, Document Intelligence, and Agentic Audit — as 11 composable tools for any MCP-compatible client.

This is the integration layer, not the intelligence layer. The intelligence lives in the pipeline repos. This server makes it consumable through a standard protocol.

Architecture

Related MCP server: Foundry Agents MCP Server

Tools

RAG Pipeline

Tool

Description

rag_query

Single-pass RAG: retrieve + generate grounded answer with citations

rag_agent_query

Multi-agent RAG for complex, multi-part questions (slower, more thorough)

rag_index

Re-index a corpus directory into the vector store (destructive)

Document Intelligence

Tool

Description

doc_classify

Classify a document by type (SOW, Contract, Project Plan, etc.)

doc_extract

Full single-doc pipeline: classify + extract structured fields + validate

doc_assess

Multi-document assessment with cross-document analysis and narrative

doc_types

List available document types and schemas (no API call)

Agentic Audit

Tool

Description

audit_generate_questions

Generate interview questions from engagement documents

audit_process_interview

Process interview artifacts against a question framework (one app at a time)

audit_synthesize

Synthesize all results into an executive summary + Excel deliverable

Utility

Tool

Description

health

Server health check: API key, vector store, schemas, pipeline status

Quick Start

Prerequisites

  • Python 3.12+

  • Pipeline repos cloned locally (any subset — unavailable pipelines are skipped):

  • LLM provider config (LLM_PROVIDER, LLM_MODEL, LLM_API_KEY) set in environment or .env

Setup

git clone https://github.com/Brinkv3/consulting-mcp-server.git
cd consulting-mcp-server

python3.12 -m venv .venv
source .venv/bin/activate

# Install server + pipeline dependencies
pip install -r requirements.txt
pip install "llm-adapter[anthropic] @ git+https://github.com/Brinkv3/llm-adapter.git" \
    chromadb sentence-transformers PyMuPDF python-docx \
    python-pptx openpyxl pandas tiktoken

# Configure pipeline paths
cp .env.example .env
# Edit .env with your actual paths and API key

Connect to Claude Desktop

Copy the config into your Claude Desktop settings (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "consulting-mcp-server": {
      "command": "/path/to/consulting-mcp-server/.venv/bin/python",
      "args": ["src/server.py"],
      "cwd": "/path/to/consulting-mcp-server",
      "env": {
        "RAG_PIPELINE_PATH": "/path/to/rag-pipeline",
        "DOC_INTEL_PATH": "/path/to/doc-intelligence",
        "AUDIT_PATH": "/path/to/agentic-audit",
        "LLM_PROVIDER": "anthropic",
        "LLM_MODEL": "claude-sonnet-4-6",
        "LLM_API_KEY": "your-key-here"
      }
    }
  }
}

See config/claude_desktop_config.json for a complete example.

Connect to Claude Code

claude mcp add consulting-mcp-server \
  -e RAG_PIPELINE_PATH=/path/to/rag-pipeline \
  -e DOC_INTEL_PATH=/path/to/doc-intelligence \
  -e AUDIT_PATH=/path/to/agentic-audit \
  -- /path/to/consulting-mcp-server/.venv/bin/python src/server.py

Verify

Once connected, ask Claude to run health — it reports the status of each component:

Server: running
RAG pipeline: available
Doc intelligence: available
Agentic audit: available
LLM provider: anthropic
LLM API key: set
Vector store: found
Schemas: found (6 types)

Architecture

MCP Client (Claude Desktop / Claude Code / any MCP client)
      │ (MCP protocol over stdio)
      ▼
consulting-mcp-server
  ├── server.py         → MCP server entry point, tool registration
  ├── rag_tools.py      → Tool handlers wrapping RAG pipeline
  ├── doc_tools.py      → Tool handlers wrapping doc intelligence
  ├── audit_tools.py    → Tool handlers wrapping agentic audit
  └── utils.py          → Config, path validation, pipeline imports
      │                    │                    │
      ▼                    ▼                    ▼
  RAG Pipeline        Doc Intelligence     Agentic Audit
  (path-based import) (path-based import)  (path-based import)

All three pipelines use src/ as their package name. The server imports them sequentially, flushing sys.modules between imports to avoid namespace collisions. Each pipeline is optional — if a path isn't configured, its tools report "unavailable" and the rest of the server works normally.

Tests

source .venv/bin/activate
pytest tests/ -v

License

MIT (c) 2026 Carter Brinkley Consulting LLC

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Foundry Agents MCP Server

    denniszielke
    A
    license
    A
    quality
    D
    maintenance
    Exposes Azure AI Foundry agents, workflows, and AI Search vector-database capabilities as MCP tools, enabling natural language interaction with agents, semantic search, and index management.
    10
    2
    MIT

  • RAG MCP Adapter

    ufigiabhi
    F
    license
    Not graded
    quality
    C
    maintenance
    Exposes an existing RAG API as MCP tools, enabling health checks and document-based question answering with source evidence.
    -

  • RAG MCP Server

    arbaz-builds
    F
    license
    Not graded
    quality
    B
    maintenance
    Exposes a Retrieval-Augmented Generation pipeline as MCP tools, allowing users to index documents and query them through any MCP-compatible client like Claude or IDEs.
    -

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Brinkv3/consulting-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server