AGENTLED TOOLS

56 tools from the Agentled MCP Server, categorised by risk level.

View the Agentled policy →

READ TOOLS

29
get_agent Get full details of an agent including its config, files, and linked proactive agent. get_app_actions Get detailed action schemas for a specific app. Returns input parameters, output fields, and credit costs. Use this to understand exactly what inpu... get_branding Get the workspace's whitelabel branding configuration. Returns the current branding settings: displayName, logoUrl, tagline, primaryColor, primaryC... get_draft Get the draft snapshot for a live workflow. When you update a live workflow, changes go to a draft instead of modifying the live pipeline. Use this... get_execution Get full execution details including results from each completed step. The executionContent field maps stepId -> step output data. Use this to insp... get_knowledge_rows Fetch sample rows from a knowledge list. Use this to inspect actual data — see example payloads from investor/deal lists. Returns rows with their f... get_knowledge_text Fetch a text-type knowledge entry by key. Use this to access text-based knowledge like feedback files, notes, or configuration text stored in the w... get_scoring_history Fetch scoring history for entities from the Knowledge Graph. Returns past scoring decisions (PROCEED_TO_IC, HOLD_FOR_REVIEW, REPOSITION, SCORED) wi... get_step_schema Get the full schema of allowed fields on workflow steps (PipelineStep type). Returns field names, types, descriptions, grouped by category. Use thi... get_timeline Get a single timeline (step execution record) by ID. Returns the full timeline including eventContent (step output), status, metadata, and context.... get_workflow Get full details of a workflow including all steps, context, metadata, and configuration. Also returns hasDraftSnapshot (boolean) and draftSnapshot... get_workspace Get workspace company info, offerings, and knowledge schema overview. Returns company details (name, industry, size, offerings) and a summary of al... get_workspace_company_profile Get the workspace company profile and its offerings. Returns the company record used for workspace setup, including company description, URLs, and ... list_agents List all agents in the workspace. Agents are higher-level entities that wrap proactive agents with instructions, files, and identity. They manage t... list_apps List all available apps/integrations in Agentled. Returns app names, descriptions, and action summaries. Use this to discover what integrations are... list_connections List all connected integrations for the workspace. Returns a unified list of connections from all sources: - OAuth connections (via Composio) - API... list_executions List recent executions for a workflow. Returns execution id, status, timestamps. list_knowledge_lists List all knowledge list schemas with field definitions, row counts, and metadata. Returns detailed information about each list including fields, so... list_models List all supported AI models for workflow steps. Returns model ID, provider, display name, tier (mini/standard/max), credit cost, and category. Us... list_snapshots List available config snapshots for a workflow. Snapshots are automatically captured before every external API update, allowing you to restore a pr... 2/5 list_timelines List timelines (step execution records) for a specific execution. Each timeline represents a step that ran, with its status, output, and metadata. ... list_workflows List all workflows in the workspace. Returns id, name, status, goal for each. query_kg_edges Traverse Knowledge Graph edges by entity name and/or relationship type. Returns edges with source/target node IDs, relations, scores, and metadata.... read_step_output Read the full output from a previous workflow step. Use this tool when a step output was deferred as a tool reference in a prompt — you will see a... retry_execution Retry a failed step in a workflow execution. If no timelineId is provided, the most recent failed timeline is automatically detected and retried. T... test_ai_action Test an AI prompt in isolation without creating a workflow or execution. Pass a prompt template with {{variable}} syntax and variable values to run... test_app_action Test an app action in isolation without creating a workflow or execution. Pass the appId and actionId (from list_apps / get_app_actions) plus input... test_code_action Test a code step in isolation without creating a workflow or execution. Pass JavaScript code with optional {{variable}} template syntax and variabl... 2/5 validate_workflow Validate a workflow's pipeline definition. Returns structured errors per step. Use this after creating or updating a workflow to check for: - Missi...

WRITE TOOLS

18
add_step Add a new step to a workflow with automatic positioning and next-pointer rewiring. Provide the full step object (id, type, name, and type-specific... 2/5 chat_with_agent Send a message to a specific agent. The agent's instructions are used as the system prompt. Supports multi-turn conversations via session_id. 2/5 create_agent Create a new agent with name, instructions, and optional proactive agent configuration. Key fields: - name: Agent display name - instructions: Sys... 2/5 create_snapshot Create a manual config snapshot of a workflow's current state. Use this to save a checkpoint before making changes, so you can restore later if nee... 2/5 create_workflow Create a new workflow from a pipeline definition. The pipeline object should include: - name (required): Workflow name - goal: What the workflow do... 2/5 export_workflow Export a workflow as portable JSON for cross-environment transfer. Returns a self-contained WorkflowExport object with all steps, context, metadata... 2/5 import_n8n_workflow Create a new Agentled workflow from an n8n JSON import. Behavior: - runs deterministic import preview - creates workflow in preflight draft mode -... 2/5 import_workflow Import a workflow from an export JSON into this workspace. Accepts the full WorkflowExport object (from export_workflow) and creates a new workflow... 2/5 preview_n8n_import Preview a deterministic n8n import from JSON. Returns: - normalized import hash and IR - mapped step graph - unsupported nodes + remediation - warn... 2/5 promote_draft Promote the draft snapshot to live. This overwrites the live pipeline config with the draft contents, then deletes the draft snapshot. A pre-promot... 2/5 publish_workflow Change the status of a workflow (publish, pause, or archive). Valid transitions: created/draft -> live, live -> paused, paused -> live, any -> arch... 2/5 restore_snapshot Restore a workflow to a previous config snapshot. Use list_snapshots first to find the snapshot ID. This will revert the workflow's steps, context,... 2/5 update_agent Update an agent's name, description, instructions, or configuration. Updating instructions automatically syncs to the linked proactive agent's AI e... 2/5 update_branding Update the workspace's whitelabel branding configuration. Set any combination of branding fields. Pass null or empty string to clear a field. Fiel... 2/5 update_step Update a single step in a workflow by step ID. Only the specified fields are merged — all other steps and fields remain unchanged. This is SAFER th... 2/5 update_workflow Update an existing workflow. Provide only the fields you want to change. IMPORTANT: If the workflow is live, config edits (steps, context, name, e... 2/5 update_workspace_company_profile Update top-level workspace company profile fields. Use this for company identity and summary information such as name, industry, size, logo, websit... 2/5 upsert_workspace_company_offerings Create new workspace company offerings or update existing ones. Pass offerings with an id to update them. Omit id to create a new offering. This to... 2/5

DESTRUCTIVE TOOLS

5

EXECUTE TOOLS

4
How many tools does the Agentled MCP server have? +

The Agentled MCP server exposes 56 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Agentled tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Agentled server.

What risk categories do Agentled tools fall into? +

Agentled tools are categorised as Read (29), Write (18), Destructive (5), Execute (4). Each category has a recommended default policy.

Enforce policies on Agentled

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.