MCPBundles Hub

Choose Your Path

Two Ways to Connect

Use the MCP URL with any client, or install the CLI for terminal-first workflows

MCP URL

Add one URL to Claude, Cursor, ChatGPT, VS Code, or any MCP client. All your enabled MCP servers appear as tools instantly.

https://mcp.mcpbundles.com/hub/

→Works with any MCP-compatible client
→Browser-based setup via dashboard
→OAuth authentication built in

CLI

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.

$ pip install mcpbundles

$ mcpbundles init

→Claude Code, Cursor, Windsurf, any coding agent
→Auto-generates SKILL.md with domain knowledge
→Call tools directly: mcpbundles call <tool>

Full CLI documentation

Programmatic Tool Calling

How the Hub Works

Tool overload kills AI performance. The Hub solves it — your AI discovers tools on-demand and writes code to orchestrate them.

Discover

AI starts with server discovery through discover_mcp_servers and list_connected_mcp_servers. It chooses a server before listing tools — never sees 1,000+ tools at once.

Code

AI writes Python using code_execution to chain tools across MCP servers — processing hundreds of records in a single call.

Insight

The code runs behind the scenes. You get the answer — "7 deals need attention" — not 200 raw records dumped in chat.

34 Tools

Hub Tools

These are the meta-tools your AI uses to discover, execute, and manage everything in your workspace. MCP server tools (HubSpot, Stripe, etc.) are accessed through code_execution after choosing a server.

Discover
2

discover_mcp_servers

Browse the full catalog of available MCP servers

describe_tool

Get the full schema and description for any tool

Code Execution
1

code_execution

Write and execute Python to chain tools across MCP servers — process hundreds of records in one call

Agents
7

get_agents

List your configured agents

list_agent_runs

View run history for an agent

upsert_agent

Create or update an agent configuration

upsert_agent_skill

Attach a skill to an agent

delete_agent

Remove an agent

delete_agent_skill

Remove a skill from an agent

trigger_agent_run

Kick off an agent run

Connect & Operate
7

list_connected_mcp_servers

List your enabled MCP servers and their tools

connect_mcp_server

Add a remote MCP server or REST API, or enable / configure / compose servers

turn_off_mcp_server

Turn off a server but keep saved credentials and settings

remove_mcp_server_from_workspace

Remove a shared catalog server from the workspace

delete_private_mcp_server

Delete a private MCP server you created or imported

test_connected_mcp_server

Run validation checks on a server's configuration

health_check

Confirm the Hub is running and responsive

Workspace Management
5

list_tool_executions

View your tool execution history

list_credentials

List configured credentials

upsert_credential

Add or update API keys and OAuth tokens

delete_credential

Remove a stored credential

get_workspace_usage

View workspace usage and plan limits

Publish
12

publish_mcp_server

Publish a workspace-connected MCP server, using same-domain email or a proof token

start_publish_ownership_verification

Start well-known email proof when same-domain publishing is not available

complete_publish_ownership_verification

Complete well-known email proof and receive a publish token

edit_published_mcp_server

Update a published server's directory metadata and skill content

refresh_published_mcp_server_metadata

Refresh a published server's tool, auth, and transport metadata

score_published_mcp_server

Run quality scoring for a published server's tools and skill content

check_published_mcp_server_claim

See whether a directory listing can be claimed

start_mcp_server_claim

Start ownership proof for an existing published server

complete_mcp_server_claim

Complete ownership proof and claim a published server

archive_published_mcp_server

Hide a published server without deleting its history

republish_mcp_server

Restore an archived server to the public directory

delete_published_mcp_server

Permanently delete a published server listing

Auto-Generated Domain Knowledge

The CLI Skill

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.

SKILL.md

Discovery workflow, argument formats, rules for tool names with hash suffixes

argument-formats.md

Key=value, typed JSON with :=, from file, from stdin

common-patterns.md

Reusable Python script templates for discovery, chaining, and bulk operations

MCPBundles CLI Skill
SKILL.md

Auto-generated by mcpbundles init — teaches your AI the discovery-first workflow for 10,000+ tools.

MCPBundles CLI

Tools are organized into MCP servers (e.g. stripe, hubspot-crm). mcpbundles tools shows hub meta-tools only. Use --server <slug> for service tools.

Workflow

mcpbundles call discover_mcp_servers # 1. find MCP server slug mcpbundles tools --server <slug> # 2. find tool name (has hash suffix like -5b7) mcpbundles tools <tool-name> --server <slug> # 3. get schema mcpbundles call <tool-name> --server <slug> -- k=v # 4. call it

Arguments

mcpbundles call <tool> --server <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(server="slug", ...) mcpbundles exec "r = await health_check(); print(r)" # inline

Rules

Tool names have hash suffixes — always discover first, never guess
server= required in exec — await tool(server="slug", ...) for MCP server tools; platform tools (health_check, discover_mcp_servers) omit it
Variables don't persist between exec calls — put everything in one script
Multiple connections — use --as <name> on every command

REST API Providers

Register any REST API with connect_mcp_server using base_url instead of server_url. Creates provider + MCP server + credential with one api_request tool. Auth is auto-injected.

mcpbundles call connect_mcp_server -- base_url="https://api.example.com/v1" api_key="sk-xxx" name="Example" mcpbundles call connect_mcp_server -- base_url="..." api_key="..." auth_type="header" auth_header_name="X-API-Key" mcpbundles call connect_mcp_server -- base_url="..." auth_type="none"

auth_type: bearer (default), header, query_param, basic, none.

Real Workflows

What the Hub Makes Possible

Cross-Service Analysis

"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.

Content Performance

"What topics should I write about?" AI pulls traffic data, identifies top performers, checks keyword opportunities in Ahrefs, and gives specific topic recommendations.

Customer Health Scoring

"Flag accounts with declining engagement." AI identifies top accounts by revenue, pulls engagement metrics, checks support history, and ranks by risk.

CLI-Driven Automation

"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.

Pick Your Approach

Focused MCP Servers vs The Hub

Use focused MCP servers for everyday tasks, switch to the Hub when you need to combine data across services.

Focused MCP Servers

Connect a specific MCP server to your client. AI sees only the 5-15 tools it needs — fast, reliable, no confusion.

→ Best for daily tasks in one domain
→ Each MCP server includes a SKILL.md
→ Works with any MCP client

Browse MCP servers

The Hub

One endpoint, all your MCP servers. AI discovers tools on-demand and writes code to chain them — returns insights, not data dumps.

→ Best for cross-service analysis
→ AI writes code to chain tools together
→ Available via MCP URL or CLI

How code execution works

Get started in 30 seconds

Your AI Deserves All the Tools.

One endpoint. 10,000+ pre-authenticated tools. MCP URL or CLI — your choice.