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., "@bp-mcp-idd Summarize portfolio risks and resource allocation"
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.
A read-only Model Context Protocol (MCP) server for BigPicture.
It lets technical enterprise users query live BigPicture portfolio data — projects, timelines, resources, risk and boards — from any MCP-compatible AI client, and puts a source citation on every answer, so a number in a chat window can be traced back to the endpoint and box it came from.
Nothing is built yet. This commit exists so the repository has a HEAD.
The code in this repository is written by sandboxed agents driven by isolated-claude, following an intent-driven-development workflow. Each run clones this repository into a hardened container, works, and is harvested as a patch.
Related MCP server: Backlog MCP Server
Read-only. The server never writes to BigPicture — no endpoint that mutates state is exposed as a tool, and that is a property to be tested, not a convention.
area | what a client should be able to ask |
Portfolio structure | the box hierarchy, box types, what contains what |
Timelines | task dates and ranges within a box |
Resources | teams, members, allocations, capacity, absences, skills |
Risk | the risk register for a box |
Boards | board configuration and contents |
Objectives | OKRs — objectives, key results, updates |
The BigPicture public API takes a token in an Authorization: Bearer <token> header. Tokens are
created and revoked in the BigPicture UI. The API index used to build this server is published at
https://developer.bigpicture.one/llms.txt; endpoints live under paths such as
/public/ppm/box/box-hierarchy.
A token is a credential. It is read from the environment, never committed, and never echoed into a tool result.
This server cannot be deployed
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Official Microsoft MCP Server to query Microsoft Entra data using natural language
Jepto MCP server that provides access to client knowledgebase & analytics for connected data sources
