Use the MCP URL with any client, or install the CLI for terminal-first workflows
Add one URL to Claude, Cursor, ChatGPT, VS Code, or any MCP client. All your enabled bundles appear as tools instantly.
https://mcp.mcpbundles.com/hub/Two commands and your AI coding agent has access to every tool. Auto-generates a SKILL.md so your AI knows how to use them.
mcpbundles call <tool>Tool overload kills AI performance. The Hub solves it — your AI discovers tools on-demand and writes code to orchestrate them.
AI starts with meta-tools like search_tools and get_bundle_servers. It finds what it needs on-demand — never sees 1,000+ tools at once.
AI writes Python using code_execution to chain tools across bundles — processing hundreds of records in a single call.
The code runs behind the scenes. You get the answer — "7 deals need attention" — not 200 raw records dumped in chat.
These are the meta-tools your AI uses to discover, execute, and manage everything in your workspace. Bundle-specific tools (HubSpot, Stripe, etc.) are accessed through code_execution and search_tools.
browse_bundle_serversBrowse the full catalog of available MCP servers
get_bundle_serversList your enabled bundle servers and their tools
upsert_bundle_serverEnable, disable, or configure a bundle server
upsert_providerAdd any remote MCP server or REST API by URL
search_toolsSearch across all tools in all your enabled bundles
get_tool_infoGet the full schema and description for any tool
code_executionWrite and execute Python to chain tools across bundles — process hundreds of records in one call
get_agentsList your configured agents
get_agent_runsView run history for an agent
upsert_agentCreate or update an agent configuration
upsert_agent_skillAttach a skill to an agent
delete_agentRemove an agent
delete_agent_skillRemove a skill from an agent
trigger_agent_runKick off an agent run
validate_bundle_serverRun validation checks on a bundle's configuration
health_checkConfirm the Hub is running and responsive
get_executionsView your tool execution history
get_credentialsList configured provider credentials
upsert_credentialAdd or update API keys and OAuth tokens
delete_credentialRemove a stored credential
delete_bundle_serverRemove a bundle server
delete_providerRemove a provider
open_mcpbundles_appOpen the interactive Hub dashboard — agents, runs, bundles, and system health
When you run mcpbundles init, it writes a SKILL.md into your project. Your AI agent immediately knows how to discover and use 10,000+ tools — no prompt engineering required.
Discovery workflow, argument formats, rules for tool names with hash suffixes
Key=value, typed JSON with :=, from file, from stdin
Reusable Python script templates for discovery, chaining, and bulk operations
Auto-generated by mcpbundles init — teaches your AI the discovery-first workflow for 10,000+ tools.
Tools are organized into bundles (e.g. stripe, hubspot-crm).
mcpbundles tools shows hub meta-tools only. Use --bundle <slug> for service tools.
mcpbundles call get_bundles # 1. find bundle slug
mcpbundles call search_tools -- query="send email" # or search across all
mcpbundles tools --bundle <slug> # 2. find tool name (has hash suffix like -5b7)
mcpbundles tools <tool-name> --bundle <slug> # 3. get schema
mcpbundles call <tool-name> --bundle <slug> -- k=v # 4. call it
mcpbundles call <tool> --bundle <slug> -- key=value limit:=5 tags:='["a","b"]'
For complex/nested JSON, use exec -f to avoid shell quoting:
mcpbundles exec -f /tmp/script.py # Python with: result = await tool_name(bundle="slug", ...)
mcpbundles exec "r = await health_check(); print(r)" # inline
bundle= required in exec — await tool(bundle="slug", ...) for bundle tools; platform tools (health_check, get_bundles) omit itexec calls — put everything in one script--as <name> on every commandRegister any REST API with upsert_provider using base_url instead of server_url.
Creates provider + bundle + credential with one api_request tool. Auth is auto-injected.
mcpbundles call upsert_provider -- base_url="https://api.example.com/v1" api_key="sk-xxx" name="Example"
mcpbundles call upsert_provider -- base_url="..." api_key="..." auth_type="header" auth_header_name="X-API-Key"
mcpbundles call upsert_provider -- base_url="..." auth_type="none"
auth_type: bearer (default), header, query_param, basic, none.
"Which deals have gone cold and have support issues?" AI checks HubSpot deals, cross-references your ticketing system, and tells you exactly which 7 need attention.
"What topics should I write about?" AI pulls traffic data, identifies top performers, checks keyword opportunities in Ahrefs, and gives specific topic recommendations.
"Flag accounts with declining engagement." AI identifies top accounts by revenue, pulls engagement metrics, checks support history, and ranks by risk.
"Process all unresolved support tickets." Your coding agent writes a script that fetches tickets, categorizes them, updates the CRM, and Slacks the team — all from your terminal.
Use focused bundles for everyday tasks, switch to the Hub when you need to combine data across services.
Connect a specific bundle to your client. AI sees only the 5-15 tools it needs — fast, reliable, no confusion.
One endpoint, all your bundles. AI discovers tools on-demand and writes code to chain them — returns insights, not data dumps.