--- title: Warp API Integration on Truto slug: warp category: Artificial Intelligence canonical: "https://truto.one/integrations/detail/warp/" --- # Warp API Integration on Truto **Category:** Artificial Intelligence **Status:** Beta ## MCP-ready AI tools Truto exposes 27 tools for Warp that AI agents can call directly. - **list_all_warp_agents** — List available Warp agents (skills) that can be used to run tasks, discovered from accessible environments or a specific repository. Returns each agent's name and a variants array; each variant includes id, description, base_prompt, source (owner, name, skill_path, worker_host), environments, last_run_timestamp, and error. - **list_all_warp_agent_connected_self_hosted_workers** — List currently connected self-hosted workers for the authenticated team in Warp. Returns: worker_host, connection_count, connected_at, last_seen_at. Worker presence is derived from websocket heartbeats and may be briefly stale. - **list_all_warp_run_transcripts** — Retrieve the raw conversation transcript for a warp agent run. The API issues a 302 redirect to a time-limited download URL containing the transcript content; no structured JSON body is returned on success. Required: run_id. - **create_a_warp_agent_run** — Spawn a Warp cloud agent run with a prompt and optional configuration. The agent is queued for execution and assigned a unique run ID. Returns: run_id, task_id, state, at_capacity. Required: prompt. - **list_all_warp_agent_runs** — List Warp agent runs with optional filtering by state, creator, model, date range, skill, and more. Results default to sort_by=updated_at and sort_order=desc. Returns: run_id, task_id, title, state, execution_location, prompt, created_at, updated_at, run_time, started_at, status_message, source, schedule, session_id, session_link, trigger_url, creator, executor, request_usage, agent_config,… - **get_single_warp_agent_run_by_id** — Get detailed information about a specific Warp agent run by id, including the full prompt, session link, and resolved agent configuration. Returns: run_id, task_id, title, state, execution_location, prompt, created_at, updated_at, run_time, started_at, status_message, source, schedule, session_id, session_link, trigger_url, creator, executor, request_usage, agent_config, conversation_id,… - **warp_agent_runs_cancel** — Cancel a Warp agent run that is queued or in progress. Returns the run_id string of the cancelled run. Required: run_id. Cannot cancel runs already in a terminal state (SUCCEEDED, FAILED, ERROR, BLOCKED, CANCELLED); PENDING-state runs return 409. - **list_all_warp_run_timelines** — List chronological setup and lifecycle timeline events for a warp agent run. Returns an events array where each item includes event_uuid, run_id, execution_id, event_type, occurred_at, and payload. Required: run_id. - **list_all_warp_run_conversations** — Get normalized run conversation in Warp by id. Returns conversation_id, steps with descriptions, summaries, timestamps, and nested messages showing user and system interactions. - **create_a_warp_run_followup** — Submit a follow-up message to an existing warp agent run. The server transparently routes the message based on the run's current state (queued, actively running, or ended). Returns an empty 200 response on success. Required: run_id. - **get_single_warp_agent_conversation_by_id** — Get a normalized conversation in Warp by id. Returns conversation_id, steps including step descriptions, timestamps, and messages with their content. - **list_all_warp_agent_schedules** — List all scheduled agents accessible to the authenticated user in Warp, sorted alphabetically by name. Returns: id, name, cron_schedule, enabled, prompt, last_spawn_error, agent_config, agent_uid, environment, created_at, updated_at, created_by, updated_by, history, scope. - **create_a_warp_agent_schedule** — Create a new scheduled agent in Warp that runs automatically on a cron expression. Returns the created agent including id, name, cron_schedule, enabled, prompt, agent_config, agent_uid, created_at, history, and scope. Required: name, cron_schedule. - **get_single_warp_agent_schedule_by_id** — Get a scheduled agent by id in Warp, including its full configuration, run history, and next scheduled execution time. Returns: id, name, cron_schedule, enabled, prompt, last_spawn_error, agent_config, agent_uid, environment, created_at, updated_at, created_by, updated_by, history, scope. Required: id. - **update_a_warp_agent_schedule_by_id** — Update an existing scheduled agent in Warp. Returns the updated agent including id, name, cron_schedule, enabled, prompt, agent_config, agent_uid, created_at, history, and scope. Required: id, name, cron_schedule, enabled. - **delete_a_warp_agent_schedule_by_id** — Delete a scheduled agent by id in Warp, stopping all future scheduled runs. Returns a 200 response on success. Required: id. - **warp_agent_schedules_pause** — Pause a scheduled agent in Warp, preventing it from running until resumed. Returns the updated schedule object including id, name, cron_schedule, enabled, prompt, agent_config, agent_uid, created_at, and updated_at. Required: schedule_id. - **warp_agent_schedules_resume** — Resume a paused scheduled agent in Warp so it begins running again according to its cron schedule. Returns the updated schedule object including id, name, cron_schedule, enabled, prompt, agent_config, agent_uid, created_at, and updated_at. Required: schedule_id. - **list_all_warp_agent_environments** — List cloud environments accessible to the authenticated principal in warp, including environments the caller owns, has been granted guest access to, or has accessed via link sharing. Returns: uid, config, last_updated, last_task_run_timestamp, last_task_created, setup_failed, scope, creator, last_editor. - **list_all_warp_agent_models** — List LLM models available to the authenticated user in Warp for agent runs. Returns per-model fields including id, display_name, provider, vision_supported, description, reasoning_level, and disable_reason (when the model is unavailable). - **get_single_warp_agent_artifact_by_id** — Get a single Warp artifact by id. For downloadable file-like artifacts returns a time-limited signed download URL; for plan artifacts returns the current content inline. Returns: artifact_uid, artifact_type, created_at, data. Required: id. - **list_all_warp_harness_support_transcripts** — Download the raw third-party harness transcript for the current task's conversation in Warp. Returns a 307 redirect to a signed download URL for the raw transcript file (e.g., claude_code.json). Only supported for non-Oz harness conversations; must be called from within a cloud agent execution environment that has an associated conversation. - **list_all_warp_agent_identities** — List all warp agent identities for the caller's team. Returns each agent's uid, name, available, description, prompt, environment_id, created_at, updated_at, base_model, skills, secrets, memory_stores, base_harness, inference_providers, and harness_auth_secrets. - **create_a_warp_agent_identity** — Create a new warp agent identity for the caller's team. Returns the created agent object including uid, name, available, created_at, updated_at, description, prompt, environment_id, base_model, secrets, skills, memory_stores, base_harness, inference_providers, and harness_auth_secrets. Required: name. - **update_a_warp_agent_identity_by_id** — Update an existing warp agent identity by id. Returns the updated agent object including uid, name, available, created_at, updated_at, description, prompt, environment_id, base_model, secrets, skills, memory_stores, base_harness, inference_providers, and harness_auth_secrets. Required: id. - **delete_a_warp_agent_identity_by_id** — Delete a warp agent identity by id. All API keys associated with the agent are deleted atomically. Returns an empty 204 response on success. Required: id. - **get_single_warp_agent_identity_by_id** — Retrieve a single Warp agent identity by id. Returns the full agent object including uid, name, available flag, created_at, updated_at, secrets, skills, memory_stores, inference_providers, base_model, base_harness, harness_auth_secrets, description, prompt, and environment_id. Required: id. ## How it works 1. **Link your customer's Warp account.** Use Truto's frontend SDK; we handle every OAuth and API key flow so you don't need to create the OAuth app. 2. **Authentication is automatic.** Truto refreshes tokens, stores credentials securely, and injects them into every API request. 3. **Call Truto's API to reach Warp.** The Proxy API is a 1-to-1 mapping of the Warp API. 4. **Get a unified response format.** Every response uses a single shape, with cursor-based pagination and data in the `result` field. ## Use cases - **Embed AI-powered incident remediation** — Incident response and observability platforms can spawn Warp cloud agents the moment an alert fires, letting agents investigate repos, propose fixes, and post results back into the on-call workflow without engineers leaving the tool. - **Automate security patch remediation with audit trails** — Security and compliance SaaS can trigger Warp agents to patch vulnerable dependencies, run tests, and open PRs, then pull full run transcripts as immutable evidence for compliance vaults. - **Ship 'Resolve with AI' inside project management tools** — Ticketing and agile platforms can turn any bug or task into an autonomous agent run, shuttling clarifying follow-ups between the AI and product managers directly in the ticket thread. - **Power internal developer portals with agent health telemetry** — IDPs can surface every scheduled Warp maintenance agent, its run timeline, and failure state so platform teams can pause, resume, and monitor autonomous workflows from a single dashboard. - **Orchestrate parallel migrations from CI/CD pipelines** — CI/CD and release tooling can fan out multiple Warp agent runs across microservices, poll for terminal states, and gate builds on the aggregated results — all without maintaining Warp's API quirks in-house. ## What you can build - **One-click agent run trigger** — Let your users kick off a Warp cloud agent run directly from your UI with a chosen environment, model, and prompt using create_a_warp_agent_run. - **Live run status and cancel controls** — Surface real-time agent progress via get_single_warp_agent_run_by_id and give users a cancel button backed by warp_agent_runs_cancel. - **In-app follow-up chat with running agents** — Embed a conversation thread that pipes clarifying questions between your users and active Warp runs using create_a_warp_run_followup and list_all_warp_run_conversations. - **Scheduled maintenance agent manager** — Give users a UI to create, pause, resume, update, and delete recurring Warp agent schedules for tasks like dependency updates or weekly triage. - **Compliance-grade transcript export** — Pull raw execution transcripts and harness support logs into your platform as immutable audit records tied to each remediation or change event. - **Self-hosted worker routing dashboard** — Show enterprise customers which of their connected self-hosted Warp workers are online and route sensitive runs to their own infrastructure. ## FAQs ### How do end users authenticate their Warp account? Truto handles the Warp auth flow for your users and manages token lifecycle, so your product only needs to reference a connection ID when making calls — no credential handling on your side. ### Which Warp operations are supported today? The integration covers agent runs (create, list, get, cancel), follow-ups, conversations, transcripts, run timelines, schedules (create, get, update, delete, pause, resume), agent identities (CRUD), environments, models, artifacts, connected self-hosted workers, and harness support transcripts. ### Can we track a long-running agent from start to finish? Yes. Trigger with create_a_warp_agent_run, poll get_single_warp_agent_run_by_id for status, stream steps via list_all_warp_run_conversations and list_all_warp_run_timelines, and pull the final transcript when the run reaches a terminal state. ### Does Truto normalize pagination and error handling for Warp? Yes. Truto abstracts Warp's pagination, retries, and rate-limit backoff behind consistent list endpoints, so your team doesn't build per-endpoint quirks. ### Can we route runs to a customer's self-hosted Warp workers? Yes. Use list_all_warp_agent_connected_self_hosted_workers to discover a customer's own workers and target them when creating runs, keeping sensitive compute on their infrastructure. ### Is there a unified API for Warp? Warp is currently exposed through Truto as a direct, tool-based integration rather than a unified AI API. You get typed access to every listed Warp operation while Truto manages auth, connection state, and normalization.