Stakeholder MCP Server

MCP server that exposes stakeholder personas for iterative product feedback

Local serverstdio

What is the Stakeholder MCP MCP server?

If you already use Stakeholder MCP, the stakeholder mcp mcp server is the piece that lets your assistant work with it directly. MCP server that exposes stakeholder personas for iterative product feedback.

What the server does

An MCP (Model Context Protocol) server that exposes stakeholder personas as tools for iterative product feedback. Each stakeholder represents a distinct role with a unique personality, expertise, and concerns.

  • 7 Pre-configured Stakeholders — Tech Lead, Product Manager, UX Designer, Security Engineer, DevOps Engineer, and two End User personas
  • Runtime Persona Management — Create, update, and delete stakeholders at runtime
  • Multi-Provider LLM Support — Uses OpenRouter for access to 100+ models (GPT-4, Claude, Gemini, Llama, etc.)
  • Flexible Consultation — Query stakeholders individually or in groups (parallel or sequential mode)
  • Multiple Transports — stdio (default) and HTTP/SSE support

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • list_stakeholders — List all available personas with optional filtering
  • get_stakeholder — Get detailed info about a specific stakeholder
  • consult_stakeholder — Query a stakeholder for feedback
  • consult_group — Query multiple stakeholders (parallel or sequential)
  • create_stakeholder — Create a new runtime stakeholder
  • update_stakeholder — Update an existing stakeholder
  • delete_stakeholder — Delete a runtime stakeholder
  • Cursor — Add the server to your MCP config. User-level: Cursor Settings → MCP → Edit config (or ~/.cursor/mcp.json). Project-level: .cursor/mcp.json in

Credentials and setup notes

Configuration is passed through the environment: OPENROUTER_API_KEY, STAKEHOLDER_MCP_CONFIG_PATH, STAKEHOLDER_MCP_DB_PATH, STAKEHOLDER_MCP_RUNTIME_STORE_PATH, STAKEHOLDER_MCP_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Stakeholder MCP's toolset — list_stakeholders, get_stakeholder, consult_stakeholder and 5 more — is a fair guide to whether it matches your workflow. It is maintained by okkimus; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
list_stakeholdersList all available personas with optional filtering
get_stakeholderGet detailed info about a specific stakeholder
consult_stakeholderQuery a stakeholder for feedback
consult_groupQuery multiple stakeholders (parallel or sequential)
create_stakeholderCreate a new runtime stakeholder
update_stakeholderUpdate an existing stakeholder
delete_stakeholderDelete a runtime stakeholder
CursorAdd the server to your MCP config. User-level: **Cursor Settings → MCP → Edit config** (or ~/.cursor/mcp.json). Project-level: .cursor/mcp.json in the repo root.

How to install the Stakeholder MCP MCP server

{
  "mcpServers": {
    "stakeholder-mcp": {
      "command": "bun",
      "args": ["run", "/path/to/stakeholder-mcp/src/index.ts"],
      "env": {
        "OPENROUTER_API_KEY": "your-key-here",
        "STAKEHOLDER_MCP_CONFIG_PATH": ".cursor/stakeholders.yaml",
        "STAKEHOLDER_MCP_DB_PATH": ".cursor/data/consultations.db",
        "STAKEHOLDER_MCP_RUNTIME_STORE_PATH": ".cursor/data/runtime-stakeholders.json"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
OPENROUTER_API_KEYCredential the server authenticates with.Yes
STAKEHOLDER_MCP_CONFIG_PATHFilesystem location the server is allowed to use.Optional
STAKEHOLDER_MCP_DB_PATHFilesystem location the server is allowed to use.Optional
STAKEHOLDER_MCP_RUNTIME_STORE_PATHFilesystem location the server is allowed to use.Optional
STAKEHOLDER_MCP_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Stakeholder MCP to list stakeholders.
  • Use Stakeholder MCP to get stakeholder.
  • Use Stakeholder MCP to consult stakeholder.

Frequently asked questions

It connects Stakeholder MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (list_stakeholders, get_stakeholder, consult_stakeholder, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Stakeholder MCP directly.