# AgentPMT Workflow Creator ## Links - Product page URL: https://www.agentpmt.com/marketplace/agentpmt-workflow-creator - Product markdown URL: https://www.agentpmt.com/marketplace/agentpmt-workflow-creator?format=agent-md - Product JSON URL: https://www.agentpmt.com/marketplace/agentpmt-workflow-creator?format=agent-json ## Overview - Product ID: 697ad12ce50ea269b242e6a6 - Type: connector - Unit type: request - Price: 0 credits - Categories: Developer Tools, AI & Machine Learning, Task Planning & Orchestration, Automation - Generated at: 2026-06-25T05:10:32.985Z ### Page Description Design, build, and publish specialized AI agent workflows that orchestrate complex multi-step automation across 170+ integrated tools. The AgentPMT Workflow Creator lets you chain together tool calls, AI reasoning steps, iterative loops, conditional branching, and human approval gates into reusable directed acyclic graph (DAG) pipelines. Build anything from simple 3-step automations to sophisticated 15-step business process pipelines that span OCR document processing, CRM updates, financial reconciliation, content generation, data analysis, notification delivery, and more. Each workflow is version-controlled, publishable, and remixable -- start from scratch or fork an existing public workflow and customize it. No code required. Define what each node does, connect them with edges, and the agent runtime handles execution, data flow between steps, and error handling. Workflows support tool nodes (execute any AgentPMT marketplace tool), prompt nodes (AI reasoning and data transformation), for_each nodes (batch processing over collections), and notify_human nodes (approval gates for high-stakes decisions). Publish workflows as reusable skills that any agent can discover and run, complete with industry tagging, time-saved estimates, and showcase examples. ### Agent Description Build and manage multi-step AI agent workflows (skill chains) that orchestrate tools, prompts, loops, and human notifications into reusable DAG pipelines. Supports creating, updating, publishing, remixing, searching, and adding showcase examples to workflows. Access a catalog of 170+ tools to chain together. Call get_instructions before starting. ## Details ### Details Design, build, and publish specialized AI agent workflows that orchestrate complex multi-step automation across 170+ integrated tools. The AgentPMT Workflow Creator lets you chain together tool calls, AI reasoning steps, iterative loops, conditional branching, and human approval gates into reusable directed acyclic graph (DAG) pipelines. Build anything from simple 3-step automations to sophisticated 15-step business process pipelines that span OCR document processing, CRM updates, financial reconciliation, content generation, data analysis, notification delivery, and more. Each workflow is version-controlled, publishable, and remixable -- start from scratch or fork an existing public workflow and customize it. No code required. Define what each node does, connect them with edges, and the agent runtime handles execution, data flow between steps, and error handling. Workflows support tool nodes (execute any AgentPMT marketplace tool), prompt nodes (AI reasoning and data transformation), for_each nodes (batch processing over collections), and notify_human nodes (approval gates for high-stakes decisions). Publish workflows as reusable skills that any agent can discover and run, complete with industry tagging, time-saved estimates, and showcase examples. ### Actions - `create_new`: Create a new workflow skill. - `update_existing`: Update an existing workflow skill draft. - `fetch_existing`: Fetch workflow skills, optionally filtered to one skill. - `search_public`: Search public workflow skills. - `publish`: Publish a workflow skill version. - `remix`: Create a remix from an existing workflow skill. - `delete`: Delete a workflow skill draft. - `fetch_tools`: Browse or search tools available for workflow nodes. - `validate`: Dry-run validate workflow graph nodes and edges without persisting. - `fetch_industry_tags`: Fetch available industry tags for workflow skills. - `add_showcase_example`: Add a single showcase example to a workflow skill. - `remove_showcase_example`: Remove a showcase example from a workflow skill by id. ### Use Cases Build custom AI agent workflows, automate multi-step business processes, chain tools together into reusable pipelines, create no-code automation workflows, orchestrate document processing pipelines, build financial reconciliation workflows, design content creation and publishing pipelines, automate data collection and reporting, create customer onboarding sequences, build monitoring and alerting workflows, remix and customize existing public workflows, publish shareable workflow skills for the AgentPMT marketplace ### Workflows Using This Tool #### Workflow Builder Agent Design, build, test, and publish custom automation workflows on AgentPMT. Walk through the complete workflow creation process from idea to published skill: define what you want to automate, discover available tools from a catalog of 170+, design multi-step DAG graphs with tool nodes, prompt nodes, branching, loops, and human notifications, then test and iterate until the workflow runs correctly. Uses the AgentPMT Workflow Creator tool directly for tool discovery, workflow creation, verification, and publishing. Covers workflow architecture, node types, edge connections, industry tagging, versioning, and publishing. Ideal for no-code automation, business process automation, task chaining, AI agent orchestration, and building reusable skill chains. - Page URL: https://www.agentpmt.com/agent-workflow-skills/workflow-builder-agent - Markdown URL: https://www.agentpmt.com/agent-workflow-skills/workflow-builder-agent?format=agent-md - Published: 2026-03-27T03:41:25.359Z ### Related Content #### AgentPMT Workflow Creator: Build Multi-Step AI Pipelines for Free - Type: article - Page URL: https://www.agentpmt.com/articles/agentpmt-workflow-creator-build-multi-step-ai-pipelines-for-free - Markdown URL: https://www.agentpmt.com/articles/agentpmt-workflow-creator-build-multi-step-ai-pipelines-for-free?format=agent-md AgentPMT launches the Workflow Creator, a free tool that lets AI agents build multi-step DAG pipelines from 170+ integrated tools -- turning single-action agents into autonomous workflow machines. ## Integration Details ### DynamicMCP - Setup page URL: https://www.agentpmt.com/dynamic-mcp - Claude setup guide: https://www.agentpmt.com/dynamic-mcp#platform=claude - ChatGPT setup guide: https://www.agentpmt.com/dynamic-mcp#platform=chatgpt - Cursor setup guide: https://www.agentpmt.com/dynamic-mcp#platform=cursor - Windsurf setup guide: https://www.agentpmt.com/dynamic-mcp#platform=windsurf Use the local router for command-based MCP clients. It forwards requests to `https://api.agentpmt.com/mcp` and does not execute tools locally. ```bash npm install -g @agentpmt/mcp-router agentpmt-setup ``` ### REST API The live page renders cURL, Python, JavaScript, and Node.js examples. Logged-in users see those examples prefilled with their own API and budget credentials. - Purchase endpoint: https://api.agentpmt.com/products/purchase - Authorization format: `Bearer ` ```bash curl -X POST "https://api.agentpmt.com/products/purchase" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer eW91ci1hcGkta2V5LWhlcmU6eW91ci1idWRnZXQta2V5LWhlcmU=" \ -d '{ "product_id": "697ad12ce50ea269b242e6a6", "parameters": { "action": "create_new" } }' ``` ### Autonomous Agents Autonomous agents can access this tool through AgentAddress credit balances or direct x402 payments. Use the Autonomous Agent API reference for endpoint shapes after choosing the access pattern below. - Autonomous Agent API reference URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents - Autonomous Agent API reference markdown URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents?format=agent-md - Credit-Based Access Using AgentAddress: https://www.agentpmt.com/docs/autonomous-agents/credit-based-tool-usage-with-agentaddress - AgentAddress is preferred for persistent file access, stored platform state, and maximum tool use ability across repeated calls. - Direct x402 is for independent one-off tool calls that do not require shared files or stored platform state. - Direct x402 public payments: USDC on Base, Arbitrum, Optimism, Polygon, and Avalanche. #### Product Skill Package This product has a published Agent Skill package for product-specific operating instructions. - Skill slug: agentpmt-workflow-creator - Version: 1.0.0 - Download SKILL.md: https://raw.githubusercontent.com/AgentPMT/agent-skills/main/skills/agentpmt-workflow-creator/SKILL.md - Package source: https://github.com/AgentPMT/agent-skills/tree/main/skills/agentpmt-workflow-creator - OpenClaw listing: https://clawhub.ai/agentpmt/agentpmt-workflow-creator - OpenClaw install: `openclaw skills install agentpmt-workflow-creator` - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-workflow-creator` - Last published: 2026-06-24T10:25:33.220Z ### Schema #### Parameters - Schema type: actions ```json { "actions": { "create_new": { "description": "Create a new workflow skill.", "properties": { "name": { "type": "string", "description": "Workflow skill name", "required": false }, "description": { "type": "string", "description": "Workflow skill description", "required": false }, "industry_tags": { "type": "array", "description": "List of industry tag names to associate with this workflow", "required": false, "items": { "type": "string", "description": "" } }, "time_saved_minutes": { "type": "number", "description": "Estimated minutes saved (>= 0)", "required": false, "minimum": 0 }, "visibility": { "type": "string", "description": "Visibility: private or public", "required": false }, "mcp_server_name": { "type": "string", "description": "MCP server name (default: agentpmt)", "required": false }, "default_export_target": { "type": "string", "description": "Default export target: mcp or rest", "required": false }, "nodes": { "type": "array", "description": "Workflow graph nodes - array of SkillChainNode objects", "required": false, "items": { "type": "object", "description": "" } }, "edges": { "type": "array", "description": "Workflow graph edges - array with {id, from, to, condition, sourceHandle?, targetHandle?}", "required": false, "items": { "type": "object", "description": "" } }, "remixed_from_skill_id": { "type": "string", "description": "Source skill ID when creating a remix", "required": false }, "remixed_from_skill_name": { "type": "string", "description": "Source skill name when creating a remix", "required": false } } }, "update_existing": { "description": "Update an existing workflow skill draft.", "properties": { "skill_id": { "type": "string", "description": "Skill chain ObjectId or slug (required for update, publish, remix, delete; optional for fetch)", "required": false }, "name": { "type": "string", "description": "Workflow skill name", "required": false }, "description": { "type": "string", "description": "Workflow skill description", "required": false }, "industry_tags": { "type": "array", "description": "List of industry tag names to associate with this workflow", "required": false, "items": { "type": "string", "description": "" } }, "time_saved_minutes": { "type": "number", "description": "Estimated minutes saved (>= 0)", "required": false, "minimum": 0 }, "visibility": { "type": "string", "description": "Visibility: private or public", "required": false }, "mcp_server_name": { "type": "string", "description": "MCP server name (default: agentpmt)", "required": false }, "default_export_target": { "type": "string", "description": "Default export target: mcp or rest", "required": false }, "nodes": { "type": "array", "description": "Workflow graph nodes - array of SkillChainNode objects", "required": false, "items": { "type": "object", "description": "" } }, "edges": { "type": "array", "description": "Workflow graph edges - array with {id, from, to, condition, sourceHandle?, targetHandle?}", "required": false, "items": { "type": "object", "description": "" } } } }, "fetch_existing": { "description": "Fetch workflow skills, optionally filtered to one skill.", "properties": { "skill_id": { "type": "string", "description": "Skill chain ObjectId or slug (required for update, publish, remix, delete; optional for fetch)", "required": false }, "include_published_only": { "type": "boolean", "description": "For fetch_existing: only return skills that have been published", "required": false } } }, "search_public": { "description": "Search public workflow skills.", "properties": { "query": { "type": "string", "description": "Search query over name/description (case-insensitive)", "required": false }, "categories": { "type": "string", "description": "Comma-separated category names to filter by (for search_public)", "required": false }, "industry_tags_filter": { "type": "string", "description": "Comma-separated industry tag names to filter by (for search_public)", "required": false }, "publisher": { "type": "string", "description": "Filter by publisher username (case-insensitive substring match, for search_public)", "required": false }, "limit": { "type": "integer", "description": "Maximum results to return (1-200)", "required": false, "default": 50, "minimum": 1, "maximum": 200 }, "skip": { "type": "integer", "description": "Number of results to skip for pagination", "required": false, "minimum": 0 } } }, "publish": { "description": "Publish a workflow skill version.", "properties": { "skill_id": { "type": "string", "description": "Skill chain ObjectId or slug (required for update, publish, remix, delete; optional for fetch)", "required": false }, "version_bump": { "type": "string", "description": "Version bump type for publish: major, minor, patch, or auto", "required": false } } }, "remix": { "description": "Create a remix from an existing workflow skill.", "properties": { "skill_id": { "type": "string", "description": "Skill chain ObjectId or slug (required for update, publish, remix, delete; optional for fetch)", "required": false } } }, "delete": { "description": "Delete a workflow skill draft.", "properties": { "skill_id": { "type": "string", "description": "Skill chain ObjectId or slug (required for update, publish, remix, delete; optional for fetch)", "required": false } } }, "fetch_tools": { "description": "Browse or search tools available for workflow nodes.", "properties": { "tool_search": { "type": "string", "description": "Search query for tools in fetch_tools action", "required": false }, "sort_by": { "type": "string", "description": "Sort order for fetch_tools browse (no search query). 'recently_updated' or 'name'.", "required": false, "default": "recently_updated", "enum": [ "recently_updated", "name" ] }, "exclude_private_tools": { "type": "boolean", "description": "If true, omit private tools from fetch_tools results", "required": false }, "limit": { "type": "integer", "description": "Maximum results to return (1-200)", "required": false, "default": 50, "minimum": 1, "maximum": 200 }, "skip": { "type": "integer", "description": "Number of results to skip for pagination", "required": false, "minimum": 0 } } }, "get_instructions": { "description": "Fetch usage instructions for workflow skill management." }, "validate": { "description": "Dry-run validate workflow graph nodes and edges without persisting.", "properties": { "nodes": { "type": "array", "description": "Workflow graph nodes - array of SkillChainNode objects", "required": false, "items": { "type": "object", "description": "" } }, "edges": { "type": "array", "description": "Workflow graph edges - array with {id, from, to, condition, sourceHandle?, targetHandle?}", "required": false, "items": { "type": "object", "description": "" } }, "validation_mode": { "type": "string", "description": "Validation mode for validate action. Defaults to agent_write.", "required": false, "default": "agent_write", "enum": [ "agent_write", "draft_structure", "publish_executable" ] } } }, "fetch_industry_tags": { "description": "Fetch available industry tags for workflow skills.", "properties": { "limit": { "type": "integer", "description": "Maximum results to return (1-200)", "required": false, "default": 50, "minimum": 1, "maximum": 200 }, "skip": { "type": "integer", "description": "Number of results to skip for pagination", "required": false, "minimum": 0 } } }, "add_showcase_example": { "description": "Add a single showcase example to a workflow skill.", "properties": { "skill_id": { "type": "string", "description": "Skill chain ObjectId or slug (required for update, publish, remix, delete; optional for fetch)", "required": false }, "showcase_example": { "type": "object", "description": "Single showcase example to add (for add_showcase_example action)", "required": false } } }, "remove_showcase_example": { "description": "Remove a showcase example from a workflow skill by id.", "properties": { "skill_id": { "type": "string", "description": "Skill chain ObjectId or slug (required for update, publish, remix, delete; optional for fetch)", "required": false }, "showcase_example_id": { "type": "string", "description": "Showcase example id to remove (for remove_showcase_example action)", "required": false } } } } } ``` ### Usage Instructions # AgentPMT Workflow Creator -- Agent Instructions ## Required First Step Call `get_instructions` before creating or updating workflows. Then use `fetch_tools` to get real tool `product_id` and `product_name` values before adding tool nodes. ## Core Actions - `get_instructions` -- Retrieve this workflow authoring guide. - `fetch_tools` -- Search available tools for workflow `tool` nodes. - `search_public` -- Check existing public workflows before building from scratch. - `validate` -- Dry-run validate `nodes` and `edges` without persisting. Use this before `create_new`, `update_existing`, and `publish` when changing graph structure. - `create_new` -- Create a private or public workflow draft. - `fetch_existing` -- Fetch your workflows or one workflow by `skill_id`. - `update_existing` -- Update metadata, nodes, or edges for an existing draft. - `publish` -- Create a versioned executable snapshot. - `remix` -- Fork a public workflow into a private editable copy. - `delete` -- Delete a workflow you own. - `add_showcase_example` / `remove_showcase_example` -- Manage workflow demos. - `fetch_industry_tags` -- List valid industry tags. ## Workflow Graph Contract Persisted workflow nodes are not React Flow nodes. Do not put node configuration inside `data`. Put each node's configuration at the node root under the key matching its node type. ### Tool Node Use tool ids and names from `fetch_tools`. ```json { "id": "calculate", "type": "tool", "label": "Calculate Result", "tool": { "product_id": "689df4ac8ee2d1dd79e9035b", "product_name": "Complex Mathematics Engine", "parameters": "{\"action\":\"calculate\",\"expression\":\"2+2\"}", "instructions": "Run the calculation and return the numeric result." } } ``` Rules: `tool.product_id` must be an accessible active product ObjectId. `tool.product_name` must be non-empty for agent writes and publish. `tool.parameters`, when present, must be a JSON string. ### Prompt Node Freeform prompt: ```json { "id": "summarize", "type": "prompt", "label": "Summarize Result", "prompt": { "mode": "freeform", "text": "Summarize the calculation result for the user." } } ``` Structured prompt: ```json { "id": "classify", "type": "prompt", "label": "Classify Expense", "prompt": { "mode": "structured", "goal": "Classify each expense into a reporting category.", "inputs": "Receipt vendor, date, amount, and line item text.", "outputs": "A category label and short rationale.", "constraints": "Use only approved accounting categories." } } ``` Rules: freeform prompts require non-empty `prompt.text` for agent writes and publish. Structured prompts require non-empty `goal` and at least one of `inputs` or `outputs`. ### for_each Node Use `for_each` for iteration instead of graph cycles. Child nodes must set `parentId` to the for_each node id and must be reached by a loop edge from that parent. ```json { "id": "each-item", "type": "for_each", "label": "For Each Item", "for_each": { "item_alias": "item", "instructions": "Run the child steps once for each item in the collection." } } ``` Child prompt example: ```json { "id": "process-item", "type": "prompt", "label": "Process Item", "parentId": "each-item", "prompt": { "mode": "freeform", "text": "Process the current item." } } ``` Required for_each edges: ```json [ { "id": "loop-edge", "from": "each-item", "to": "process-item", "sourceHandle": "loop" }, { "id": "next-edge", "from": "each-item", "to": "after-loop", "sourceHandle": "next" } ] ``` Rules: for_each outgoing handles are only `loop` and `next`. A parented child is invalid unless there is a loop edge from its for_each parent to that child. ### Branch Node Use branch nodes for conditional paths. Outgoing handles must be `path_1`, `path_2`, or `path_`. ```json { "id": "choose-path", "type": "branch", "label": "Choose Path", "branch": { "description": "Select the next path based on the analysis result.", "option_count": 2, "options": { "path_1": { "name": "Approved", "description": "Proceed automatically." }, "path_2": { "name": "Review", "description": "Ask a human to review." } } } } ``` ### Merge Node Use merge nodes to join branch paths. ```json { "id": "merge-paths", "type": "merge", "label": "Merge Paths", "merge": {} } ``` ### notify_human Node Use only when human approval, credentials, budget, or judgment is genuinely required. ```json { "id": "ask-human", "type": "notify_human", "label": "Request Approval", "notify_human": { "request_type": "other", "request": "Please review and approve the generated report before delivery." } } ``` Allowed `request_type` values: `add_funds`, `enable_tool`, `enable_workflow`, `credential_setup`, `other`. ## Edge Contract Edges connect node ids with `from` and `to`. Optional handles are `sourceHandle` and `targetHandle`. ```json { "id": "edge-1", "from": "calculate", "to": "summarize" } ``` Rules: - All edge endpoints must reference existing node ids. - Graphs must be acyclic; use `for_each` for iteration. - Duplicate edges with the same `from`, `to`, and `sourceHandle` are invalid. - Only branch and for_each nodes may have multiple outgoing edges. - Edge `condition` is only allowed on branch edges. ## Position Fields Canvas-created workflows may include node `position` fields when fetched. Agent-authored payloads should omit `position` unless passing through fetched nodes unchanged. In `agent_write` validation, `position` is accepted for compatibility and removed from the canonical stored graph. Browser draft validation and publish snapshots may retain positions for rendering. ## Validation Modes Use `validate` before persisting graph changes. ```json { "action": "validate", "validation_mode": "agent_write", "nodes": [ ... ], "edges": [ ... ] } ``` Modes: - `agent_write` -- Use before `create_new` or `update_existing`. Accepts existing fetched positions and canonicalizes them away. - `draft_structure` -- Browser/editor draft validation. - `publish_executable` -- Publish-time validation. Requires at least one tool node and complete executable payloads. ## Recommended Build Flow 1. `get_instructions`. 2. `fetch_tools` for each external capability needed. 3. `search_public` to avoid rebuilding existing workflows. 4. Draft root-level `nodes` and `edges` using the contract above. 5. Call `validate` with `validation_mode: "agent_write"`. 6. Call `create_new` or `update_existing` only after validation passes. 7. Call `fetch_existing` to confirm stored graph shape. 8. Call `publish` only when the graph should become an executable versioned snapshot. ## Common Mistakes to Avoid - Do not send `{ "type": "tool", "data": { ... } }`. - Do not send `{ "type": "prompt", "data": { "prompt": "..." } }`. - Do not put `product_id` or `product_name` directly on a node; put them under `tool`. - Do not create cycles for loops; use `for_each` with `loop` and `next` edges. - Do not invent product ids. Use `fetch_tools`. - Do not publish malformed drafts to test validation. Use `validate` first. ### Additional Product Content ## Build Specialized AI Agents That Orchestrate Complex Workflows The AgentPMT Workflow Creator is a no-code workflow builder for designing multi-step AI agent pipelines. Chain together any combination of 170+ marketplace tools, AI reasoning steps, batch processing loops, and human approval gates into directed acyclic graph (DAG) workflows that run autonomously. ### How It Works Workflows are graphs of connected nodes. Each node performs a specific action, and edges define the execution order and data flow between steps: 1. **Tool Nodes** -- Execute any tool from the AgentPMT marketplace: OCR engines, accounting software, CRM systems, email services, chart generators, file storage, web scrapers, and more. 2. **Prompt Nodes** -- AI reasoning steps that transform data, make decisions, synthesize information from multiple sources, or apply business logic between tool calls. 3. **For Each Nodes** -- Iterate over collections to process records in batch: reconcile transactions one by one, send personalized emails to a list, or categorize expenses from a receipt stack. 4. **Notify Human Nodes** -- Pause execution for human approval on high-stakes decisions like financial reports, public communications, or compliance reviews. ### From Idea to Published Skill in Minutes 1. **Discover tools** -- Search the catalog of 170+ tools by keyword to find exactly what your workflow needs. 2. **Design the graph** -- Define nodes, connect them with edges, and set parameters and instructions for each step. 3. **Test and iterate** -- Fetch your workflow, verify the graph, and update nodes or edges until it runs correctly. 4. **Publish** -- Create a versioned snapshot that any agent can discover and run. Supports semantic versioning with major, minor, and patch bumps. ### Remix Instead of Rebuilding Browse published public workflows and fork any of them with a single action. Remixing creates a private copy you can customize -- change tools, adjust prompts, add or remove steps -- while preserving attribution to the original creator. ### Real-World Workflow Patterns 1. **Document Processing Pipelines** -- Upload bank statements or receipts, run OCR, extract structured data, and book transactions to accounting software. 2. **Research and Reporting** -- Aggregate data from multiple sources, analyze trends with AI reasoning, generate visualizations, and deliver briefings via email or Slack. 3. **Customer Outreach** -- Pull lead data from CRM, personalize messaging, send communications, log activity, and schedule follow-ups. 4. **Monitoring and Alerting** -- Fetch metrics, analyze against thresholds, generate alerts, and notify teams on Discord, Slack, or email. 5. **Content Pipelines** -- Research topics, draft content, create supporting visuals, publish to platforms, and notify stakeholders. ### Built for Reliability Every workflow is validated against strict graph rules: no cycles, unique node IDs, valid edge references, and proper nesting of loop children. Version control ensures published snapshots are frozen while the live workflow remains editable. ### Frequently Asked Questions #### How do I connect this tool to an external agent? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md You can install the local MCP server by opening a terminal and running: ``` npm install -g @agentpmt/mcp-router agentpmt-setup ``` This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc. Alternatively you can connect to the hosted version with this config block, no installation required: ``` { "mcpServers": { "agentpmt": { "type": "streamable-http", "url": "https://api.agentpmt.com/mcp", "headers": { "Authorization": "Bearer ", "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}" } } } } ``` [View MCP Connection Instructions](/docs/mcp-reference/connection) for more details. #### How does an external agent use this tool? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent: > Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get\_instructions' so you know how to use the tool search interface. Then call action 'get\_schema' with tool\_id 697ad12ce50ea269b242e6a6 ("AgentPMT Workflow Creator"). After reading the schema and any returned instructions, tell me what this tool can do, we are going to be using it The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT. ### Dependencies This product has no public dependency products.