skills/agentpmt-account-mcp-rest-api-setup/SKILL.md
Connect an agent, app, or integration to AgentPMT with an AgentPMT account Bearer Token. Use when configuring the hosted MCP server, the local npm MCP router, or direct REST API calls for tools, skills, workflows, and agents.
npx skillsauth add AgentPMT/agent-skills agentpmt-account-mcp-rest-api-setupInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Last updated: 2026-06-03.
If the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.
Use this skill when an agent, app, or integration has an AgentPMT account Bearer Token and should call AgentPMT tools through MCP or REST.
This path is for account-backed access. The user creates or selects an Agent Group, adds the tools and workflows the caller may use, adds any required software credentials, and copies the Agent Group Bearer Token. The Bearer Token authorizes calls against that Agent Group catalog.
Use the no-account AgentAddress/x402 skill instead when the caller does not have an AgentPMT account Bearer Token.
In AgentPMT, open the Agent Group that should own this access, add the tools, workflows, and credentials the caller may use, and copy the Bearer Token. The Bearer Token is the only account credential used for MCP and REST API calls.
Use this for agents that support remote MCP over HTTP.
Endpoint:
https://api.agentpmt.com/mcp/
Configuration shape:
{
"mcpServers": {
"agentpmt": {
"url": "https://api.agentpmt.com/mcp/",
"headers": {
"Authorization": "Bearer <agentpmt_bearer_token>"
}
}
}
}
After connecting, ask the client to list MCP tools. AgentPMT returns the tools and workflows available to the Agent Group attached to the Bearer Token.
Use this when the agent client requires a local MCP command instead of a remote MCP URL.
npm install -g @agentpmt/mcp-router
agentpmt-setup
The setup command prompts for the Bearer Token and writes the client config. For manual configuration:
{
"mcpServers": {
"agentpmt": {
"command": "npx",
"args": ["--package=@agentpmt/mcp-router@latest", "agentpmt-router"],
"env": {
"AGENTPMT_BEARER_TOKEN": "<agentpmt_bearer_token>",
"AGENTPMT_MCP_ENDPOINT": "https://api.agentpmt.com/mcp/"
}
}
}
}
The local router is a thin relay to AgentPMT. Tool execution happens in AgentPMT, not on the user's machine.
Use this only when writing an MCP client directly.
{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2025-03-26",
"clientInfo": {"name": "my-agent", "version": "1.0"},
"capabilities": {}
}
}
Then call:
{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}
Use the exact tool names returned by tools/list when calling:
{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "<tool_name_from_tools_list>",
"arguments": {}
}
}
Use REST when an agent, app, backend service, automation, or other program should integrate AgentPMT tools through authenticated HTTP calls. Additional examples and endpoint documentation is available here https://www.agentpmt.com/docs/api-reference/programmatic-access?format=agent-md
List available tools:
GET https://api.agentpmt.com/products/fetch
Authorization: Bearer <agentpmt_bearer_token>
Invoke a tool:
POST https://api.agentpmt.com/products/purchase
Authorization: Bearer <agentpmt_bearer_token>
Content-Type: application/json
Request body:
{
"name": "<product_slug_or_tool_name>",
"parameters": {
"action": "<action_name>"
}
}
Use a generated product skill for the product-specific name, action names, schema, and sample parameters.
For workflows, prefer MCP. The main AgentPMT MCP server exposes the tools, workflows, and workflow-control tools available to the Agent Group behind the Bearer Token. Use tools/list first, then call the exact returned tool name.
| Problem | Check | |---|---| | No tools appear | The Agent Group may not have tools or workflows added. | | 401 authentication error | Re-copy or rotate the Bearer Token from the Agent Group. | | Tool is missing | Add the product or workflow to the Agent Group, then refresh the MCP tool list. | | Credential error | Add the required software connection credentials to the Agent Group. |
Use these links when a related AgentPMT setup skill is not installed beside this one.
| Skill | Local path | ClawHub page | |---|---|---| | What AgentPMT is | ../what-is-agentpmt | https://clawhub.ai/agentpmt/what-is-agentpmt | | AgentPMT account MCP/REST setup | ../agentpmt-account-mcp-rest-api-setup | https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup | | No-account AgentAddress/x402 flow | ../agentpmt-no-account-agentaddress-x402 | https://clawhub.ai/agentpmt/agentpmt-no-account-agentaddress-x402 |
OpenClaw install commands:
openclaw skills install what-is-agentpmt
openclaw skills install agentpmt-account-mcp-rest-api-setup
openclaw skills install agentpmt-no-account-agentaddress-x402
skills.sh install script:
npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup
npx skills add AgentPMT/agent-skills --skill agentpmt-no-account-agentaddress-x402
tools
Plaud Transcripts Corrected With Your Own Terminology Glossary: Fixes the words your transcription keeps getting wrong, by giving the pipeline your vocabulary instead of hoping a bigger model guesses right. Every speech model mangles terms it has never seen: cell line and reagent names, drug and device names, case and matter numbers, part numbers, local spelling and number conventions, team and client names. Swapping to a different model does not fix this, because none of them have your terms e.
tools
Plaud Spoken Field Notes to a Structured Sheet: Turns a spoken site visit into a filled-in spreadsheet row, so measurements and specs never get typed up twice. Built for anyone who dictates structured details on the job rather than writing them down: window and flooring measurements, equipment specs, inspection findings, punch lists, service call notes. Say the details out loud in the same order each visit (client, room, width, drop, colour, notes) and the workflow reads each new Plaud recordin.
development
Plaud Recordings to Google Calendar Events: Puts the meetings you agree to out loud straight onto your Google Calendar, without Zapier in the middle. Plaud's own app has no Calendar integration, so this closes that gap directly: each new recording is scanned, the transcript pulled, and any genuine scheduling commitment spoken in it ("let's do Tuesday at 3", "I'll come back out Thursday morning") is extracted with the relative date resolved against the recording's own date and your timezone. Eac.
development
One Plaud Recording, Several Differently Formatted Summaries: Gets you past the one-template-per-recording ceiling. The Plaud app applies a single AutoFlow template to a recording, so if you want a short recap for yourself, a decisions-only version for the people who missed it, and a clean action list for your task manager, you are re-running or rewriting by hand. This workflow reads the transcript once and produces every format you have defined in a single pass: you list the output formats you.