Traces
Search captured spans, errors, and latency across recorded deployment versions.
Model Context Protocol
Setup instructions are available for Claude, Cursor, VS Code, ChatGPT, and other popular MCP clients. Compatibility varies by client version. Once connected, your agent can search traces, run evals, launch simulations, and start NovaPilot analyses in plain language.
MCP endpoint
ToolsGenerated
Resources16
Prompts21
One endpoint · supported Noveum workflows
Connect
Add one endpoint to the client you already use. Paste an API key for headless setups: or add just the URL and sign in with OAuth.
Point a supported MCP client at noveum.ai/api/mcp. Setup instructions are available for Cursor, Claude Code, VS Code, ChatGPT, and other clients with compatible Streamable HTTP and authentication support.
URL-only clients open a Noveum sign-in and consent screen automatically. Headless setups send an API key in the Authorization header instead.
Tools, resources, and prompts load on connect. Ask for failing traces, an eval run, or a NovaPilot analysis: in plain language.
No key required: clients that support the MCP authorization spec discover OAuth automatically. Add the URL, approve the consent screen once, and you're connected.
# Choose one authentication option.# Option A: OAuth sign-in (URL-only)claude mcp add --transport http noveum "https://noveum.ai/api/mcp"# Option B: run instead of Option A for a headless Bearer API keyclaude mcp add --transport http noveum "https://noveum.ai/api/mcp" \ --header "Authorization: Bearer NOVEUM_API_KEY"Tools · Resources · Prompts
Tools are generated from the current OpenAPI specification. Sixteen resources and 10 resource templates feed your agent real ids and slugs before it plans, while 21 prompts package guided workflows.
Supported HTTP actions generated from the current OpenAPI specification: list records, start jobs, and poll progress until terminal.
Search captured spans, errors, and latency across recorded deployment versions.
Create, version, and publish eval datasets from real traffic.
Kick off eval jobs, poll runs, and read scored results.
Build extraction pipelines and generate mappers with NovaEval.
Browse 112 published scorers or get recommendations for a dataset.
List projects, environments, usage, and organization status.
Start analyses, read reports, and manage recurring schedules.
Generate personas, launch simulations, and pull analytics.
Read-first context served as JSON: so every id, slug, and filter enum comes from real data, not guesses.
Guided prompts that spell out which tools to chain, what to poll, and when to stop. Clients decide how prompt names are displayed.
Recipes
No dashboards, no query language. Point your agent at Noveum and describe the outcome you want: these are things teams run every day.
Let your agent surface what's breaking in production and why, straight from your live traces.
Find the error traces from the last 24 hours, group them by root cause, and show me the three worst offenders with example spans.
Build a dataset from real traffic and score configured items with selected compatible scorers.
Create a dataset from yesterday's failing traces, run an evaluation with compatible scorers, and summarize the lowest-scoring items with linked evidence.
Have your agent summarize a week of usage and identify lower-cost configurations for your team to test.
Analyze my token usage and latency this week, identify the highest-cost model paths, and propose lower-cost candidates for a controlled evaluation.
Chain trace review, dataset creation, evaluation, and a NovaPilot analysis from one guided request.
Review my checkout assistant traces, build a dataset, run an evaluation, start a NovaPilot analysis, and summarize the highest-priority recommendation with its supporting evidence.
Authentication
Two modes, one endpoint. Both respect your organization's roles: a connected agent can never do more than you can.
For interactive clients. Add the URL, approve a consent screen once, and you're connected: no key to paste, no OAuth app to register.
For CI pipelines, cron jobs, and server-to-server clients that support custom Bearer headers but cannot complete browser sign-in.
noveum.read
Read projects, traces, datasets, evals, and reports
noveum.write
Create and update datasets, jobs, and settings
noveum.execute
Start jobs: ETL, evals, NovaPilot, NovaSynth
Scopes only ever narrow what a connected app can do. Your role and RBAC permissions in the organization still apply on top.
Setup available for
FAQ
Next step
Production AI agents your customers can trust.
Trusted in production by enterprise and high-growth teams