mastra-api
Mastra Development API
Interact with the Mastra dev server API to debug agents, view conversations, inspect tools and workflows, and access observability data.
Quick Start
Agent Debugging
Run these scripts/... commands from the skills/mastra-api/ directory. From repo root, prefix them with skills/mastra-api/.
# Get latest conversation
scripts/get_latest_thread.sh <agent-id> [port]
# Debug errors
scripts/debug_agent_error.sh <agent-id> [port]
# View thread messages
curl --globoff -sS \
"http://localhost:4111/api/memory/threads/THREAD_ID/messages?page=0&perPage=50&agentId=my-agent&orderBy[field]=createdAt&orderBy[direction]=DESC" \
| jq '.'
Tools and Workflows
Run these scripts/... commands from the skills/mastra-api/ directory. From repo root, prefix them with skills/mastra-api/.
# List all tools
scripts/list_tools.sh [port]
# List all workflows
scripts/list_workflows.sh [port]
# Get workflow details
scripts/get_workflow_details.sh <workflow-name> [port]
# Get workflow runs
scripts/get_workflow_runs.sh <workflow-name> [port]
Resource Listing
# List all agents
curl -sS http://localhost:4111/api/agents | jq 'keys'
# List all tools
curl -sS http://localhost:4111/api/tools | jq 'keys'
# List all workflows
curl -sS http://localhost:4111/api/workflows | jq 'keys'
Common Tasks
Debug Agent Failures
- Get latest thread:
scripts/get_latest_thread.sh my-agent - Check for errors:
scripts/debug_agent_error.sh my-agent - Inspect message content for error details
Inspect Available Resources
# See what tools an agent can use
curl -sS http://localhost:4111/api/agents | \
jq '.["my-agent"].tools | keys'
# See what workflows an agent can invoke
curl -sS http://localhost:4111/api/agents | \
jq '.["my-agent"].workflows | keys'
# List all registered tools
scripts/list_tools.sh
# List all registered workflows
scripts/list_workflows.sh
Debug Workflows
# Get workflow structure and steps
scripts/get_workflow_details.sh my-workflow
# Check workflow execution history
scripts/get_workflow_runs.sh my-workflow
# Find failed workflow runs
scripts/get_workflow_runs.sh my-workflow | \
jq '.runs[] | select(.status == "failed")'
Check Tool/Workflow Schemas
# Get tool input parameters
curl -sS http://localhost:4111/api/tools | \
jq '.YOUR_TOOL_KEY.inputSchema | fromjson.json.properties | keys'
# Get workflow input requirements
curl -sS http://localhost:4111/api/workflows/my-workflow | \
jq '.inputSchema | fromjson.json.properties | keys'
Access Observability Data
# Get traces
curl -sS http://localhost:4111/api/observability/traces | jq '.'
# Get logs
curl -sS http://localhost:4111/api/logs | jq '.'
Important Notes
Use --globoff with curl
Query parameters with brackets must use --globoff:
curl --globoff -sS "...&orderBy[field]=updatedAt&orderBy[direction]=DESC"
Without --globoff, curl treats [...] as character ranges.
API Base URLs
Standard: http://localhost:4111/api
Swagger Documentation
Complete interactive API docs: http://localhost:4111/swagger-ui
Debugging Workflow
When UI doesn't show errors clearly:
- Get latest thread -
scripts/get_latest_thread.sh <agent-id> - Extract thread ID from response
- Get messages - Use thread ID to fetch conversation
- Look for errors - Search for
"error"or"failed"fields - Review content - Inspect message content for details
This is the fastest way to debug agent issues.
Reference
See references/api_endpoints.md for:
- Complete endpoint reference
- Query parameter details
- Pagination and ordering
- Project-specific configurations
- Error handling patterns
See references/tools_and_workflows.md for:
- Tools API documentation
- Workflows API documentation
- Schema parsing examples
- Integration with agents
- Common debugging patterns
Scripts
Agent Debugging
scripts/get_latest_thread.sh <agent-id> [port] [detailed]- Get latest conversation threadscripts/debug_agent_error.sh <agent-id> [port]- Quick error debugging
Tools & Workflows
scripts/list_tools.sh [port]- List all registered tools with descriptionsscripts/list_workflows.sh [port]- List all registered workflows with stepsscripts/get_workflow_details.sh <workflow-name> [port]- Get detailed workflow informationscripts/get_workflow_runs.sh <workflow-name> [port] [page] [perPage]- Get workflow execution history
More from liatrio-labs/ai-prompts
git-commit-conventional
Create Conventional Commit messages and execute safe git commits from working tree changes. Use when users ask to create a commit, write a conventional commit message, split broad changes into multiple commits, stage only parts of files, run pre-commit before committing, or perform a quick commit-time quality review with severity guardrails.
24create-pull-request
Generate a reviewer-ready pull request or merge request title and description from branch changes. Use when a user asks to draft PR/MR content, summarize branch deltas against a base branch, or optionally create the PR with gh/glab after approval.
23create-mermaid-diagrams
Create, validate, and repair Mermaid diagrams for technical documentation with a deterministic CLI feedback loop. Use when an AI needs to create Mermaid diagrams, improve Mermaid diagram quality, validate Mermaid fences in markdown, diagnose Mermaid rendering failures, or fix Mermaid syntax and formatting issues.
21liatrio-brand-guidelines
Applies Liatrio brand guidelines to UI design, brand audits, and asset selection. Use when users request Liatrio styling, logo variants, typography or color decisions, visual polish, or formal brand compliance checks.
21branch-surgery-pr-split
Split oversized or mixed-concern branches into smaller, reviewable PR stacks with safety refs, topology selection, parity audits, and merge sequencing. Use when a PR or branch is too large, difficult to review, mixed across concerns, conflict-prone, or needs to be decomposed without losing net changes.
21uv-usage
Provides concise guidance for using uv (Python package manager), including project workflows, pip-compatible commands, Python version management, and PEP 723 inline script dependencies. Use when users mention uv, uv run, inline dependencies, PEP 723, or Python dependency/project management.
16