bpm-mcp
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., "@bpm-mcpsearch the registry for a package that auto-generates git commit messages"
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.
bpm-mcp
MCP server for BPM - discover, inspect, and install behavioral packages from within agent sessions.
Instead of switching to a terminal to manage packages, the agent can search the registry, show you what a package does, and install it after you approve.
Install
cd ~/development/bpm-mcp
uv pip install -e .Requires the BPM CLI: npm install -g @dakotafabrodev/agent-bpm
Related MCP server: skillet
Goose Config
Add to ~/.config/goose/config.yaml:
bpm:
enabled: true
type: stdio
name: BPM
description: Discover and install behavioral packages
cmd: uv
args:
- run
- --directory
- /path/to/bpm-mcp
- bpm-mcp
envs: {}
env_keys: []
timeout: 30
bundled: false
available_tools: []Tools
bpm_search(query)
Search the BPM registry by keyword. Returns matching packages with name, type, description, version, and token cost.
bpm_inspect(package_name)
Get full details about a package including its README, review status, dependencies, and peers. Use this before recommending installation.
bpm_install(package_name)
Install a package. Enforces human approval before installing. Returns an approval prompt that the human must confirm before the install proceeds.
bpm_confirm_install(package_name, always_allow?)
Execute the install after human approval. Set always_allow=true to auto-approve this package in the future.
bpm_remove(package_name)
Remove an installed package.
bpm_list()
List all installed packages and their total token cost.
bpm_set_approval_policy(mode)
Control how installs are approved:
always_ask(default) - every install requires explicit human approvalauto_approve_known- packages the human has previously approved install automatically, new packages still require approval
Approval Flow
Package installation changes agent behavior. The server enforces a two-step approval:
Agent calls
bpm_install("package-name")Server returns an approval prompt (not the install)
Human says "approve install package-name" or "always allow package-name"
Agent calls
bpm_confirm_install("package-name")orbpm_confirm_install("package-name", always_allow=true)Package installs
The approval policy is stored at ~/.bpm/mcp-policy.json.
How It Works
Search and inspect hit the usebpm.dev registry API directly (read-only, no auth needed)
Install, remove, and list shell out to the local
bpmCLIThe server never installs packages without going through the approval gate
All operations are local - no data leaves your machine except registry search queries
License
Apache 2.0
This server cannot be deployed
Maintenance
Related MCP Connectors
Search and install curated agent skills, plus bundles that get one job done in a single call.
The governed runtime for agent skills. Search the catalog and inspect a skill before running it.
Agent skills from the ProvenSkills Labs store, delivered with updates over one connector.
Search your team's shared AI-skill library, get install commands, and save skills from your agent.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to automate local software management workflows including installation, uninstallation, updates, and environment recommendations. It provides a standardized, non-interactive interface for managing system applications and tracking software versions safely.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover, install, and manage SKILL.md skills from a Git-backed registry via MCP tools for search, install, and list operations.131MIT
- AlicenseAqualityBmaintenanceEnables AI agents to autonomously search, evaluate, and install skills from the skills.sh catalog.245ISC
- AlicenseNot gradedqualityCmaintenanceEnables agents to search, create, edit, and step through JSON-based procedures with intent-driven search and step-by-step execution.MIT