Dynamic MCP Server
Link Your Agent To Any API, Tool, or Workflow with one MCP connection
One Connection | Infinite Possibilities
Connect once through AgentPMT Dynamic MCP, then use approved tools from the same agent connection.
STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections.
npm install -g @agentpmt/mcp-routeragentpmt-setupMCP endpoint for browser-based apps like ChatGPT, Claude, Grok, or any time you want a streamable connection with no local install.
https://api.agentpmt.com/mcpUse the hosted endpoint directly in clients that support remote MCP. Store your Bearer token in the client config or secret field.
{
"mcpServers": {
"agentpmt": {
"type": "streamable-http",
"url": "https://api.agentpmt.com/mcp",
"headers": {
"Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
"x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
}
}
}
}The MCP server cannot edit, read, or access anything on your computer.
The Dynamic MCP Server connects to any AI agent that supports the Model Context Protocol. Our easy setup tool automatically configures these popular platforms:
Control agent tools across your whole team from one centralized dashboard. No technical overhead, just a few clicks.
Approve or restrict tools for your entire organization with a single click. Changes propagate instantly to all agents.
Set spending limits per team or per budget. Automatic enforcement prevents overruns.
New tools become available to all agents within 30 minutes. No reinstalls, no configuration changes.
All updates propagate in real-time
Install the official package or review release notes on the npm registry page for @agentpmt/mcp-router.
Every action is logged, tracked, and auditable. Perfect for compliance, debugging, and organizational oversight.
Tools are fetched from the API on each tools/list request. Enable and disable tools from the dashboard and they update for all connected agents instantly.
Every tool invocation is recorded with full parameters, timestamps, and user context.
All tool responses, errors, and execution times are captured for full session reconstruction.
Agent instances persist across restarts with full activity history always accessible.
Every tool execution is captured with complete context in an easy-to-navigate format
0b2572d7-3645-4b33-b731-5b95cbdf3c74{
"client": "claude_code",
"platform": "linux",
"client_info": {
"ip_address": "69.136.156.79",
"user_agent": "AgentPMT-MCP/1.0"
}
}{
"product_id": "692720cb46dac36e67d0ef2e",
"parameters": {
"action": "calculate",
"expression": "integrate(x^2, x)"
},
"budget_id": "695090103119f650009bc8893"
}{
"success": true,
"instance_id": "0b2572d7-3645-4b33-b731-5b95cbdf3c74",
"response": {
"status_code": 200,
"data": {
"success": true,
"output": {
"result": "x^3/3 + C",
"execution_time": "0.23s"
}
}
},
"cost": "$0.06",
"timestamp": "2026-01-03T14:32:16Z"
}Every detail captured and organized
Structured format for quick review
From request to response
See how we compare to standard MCP servers
| Feature | Standard MCP Server | AgentPMT Dynamic MCP |
|---|---|---|
| Tool Access | Limited, pre-installed | Approved AgentPMT tool access |
| Tool Loading | Hardcoded in source | Dynamic from API |
| Updates | Requires rebuild | Automatic |
| Execution | Local process | Remote API |
| Organization Management | Individual config | Centralized dashboard |
| Auditability | Limited or none | Full activity logging |
The AgentPMT mobile app extends your Dynamic MCP setup to your phone. Get notified the moment an agent needs a decision and respond in seconds.



Real-Time Notifications
Push alerts the moment an agent needs approval -- tool access, workflows, or payments.
One-Tap Approvals
Review request details and approve or deny without opening a laptop.
Secure Payments
Biometric authentication for every credit card authorization. Card data is tokenized and encrypted.
Full Activity Feed
See every tool call, response, and status update across all your budgets in real time.