Noveum

npx add-mcp 'https://noveum.ai/api/mcp'

Drive Noveum from supported AI clients.

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.

noveum-mcp

HTTP · OAuth 2.1

MCP endpoint

ToolsGenerated

tracesdatasetsevals

Resources16

noveum://projectsnoveum://scorers

Prompts21

debug_tracesrun_evaluation

One endpoint · supported Noveum workflows

Connect the client you already use.

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.

# 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"

Bring supported Noveum workflows to your agent.

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.

Tools

Supported HTTP actions generated from the current OpenAPI specification: list records, start jobs, and poll progress until terminal.

Traces

Search captured spans, errors, and latency across recorded deployment versions.

Datasets

Create, version, and publish eval datasets from real traffic.

Evals

Kick off eval jobs, poll runs, and read scored results.

ETL pipelines

Build extraction pipelines and generate mappers with NovaEval.

Scorers

Browse 112 published scorers or get recommendations for a dataset.

Projects

List projects, environments, usage, and organization status.

NovaPilot

Start analyses, read reports, and manage recurring schedules.

NovaSynth

Generate personas, launch simulations, and pull analytics.

Resources

Read-first context served as JSON: so every id, slug, and filter enum comes from real data, not guesses.

• noveum://projects
• noveum://scorers
• noveum://filter-values
• noveum://org-status
• noveum://datasets
• noveum://eval-jobs
• noveum://etl-jobs
• noveum://novapilot-schedules
• noveum://novasynth-runs
• noveum://agent-versions
• +6 more

Prompts

Guided prompts that spell out which tools to chain, what to poll, and when to stop. Clients decide how prompt names are displayed.

• debug_traces
• run_evaluation
• analyze_with_novapilot
• optimize_costs
• trace_error_triage
• compare_eval_runs
• recommend_scorers_for_dataset
• full_agent_improvement_cycle
• test_voice_agent
• download_novapilot_report_markdown
• +10 more

Real workflows, in plain language.

No dashboards, no query language. Point your agent at Noveum and describe the outcome you want: these are things teams run every day.

Find and triage failures

debug_traces

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.

Turn traces into an evaluation

run_evaluation

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.

Cut model spend

optimize_costs

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.

Close the loop end to end

full_agent_improvement_cycle

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.

Default

OAuth 2.1 sign-in

For interactive clients. Add the URL, approve a consent screen once, and you're connected: no key to paste, no OAuth app to register.

• Per-user consent using fixed read, write, and execute scopes
• Each token is bound to a single organization, picked at consent
• Revoke any app instantly under Settings → Connected apps

Headless

Bearer API key

For CI pipelines, cron jobs, and server-to-server clients that support custom Bearer headers but cannot complete browser sign-in.

• The same key as the REST API, sent as an Authorization header
• Scoped to your organization and rotatable at any time
• Pin a specific key for scripted, reproducible setups

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.

MCP questions, answered.

What is the Noveum MCP server?

It's a remote Model Context Protocol server at noveum.ai/api/mcp. Connecting a supported client gives it secure, tool-level access to your Noveum workspace: traces, datasets, evaluations, scorers, and agent-improvement workflows, all driven in natural language.

Which AI clients can connect?

Setup instructions are available for Claude and Claude Code, Cursor, VS Code, ChatGPT developer mode, Windsurf, Cline, Replit, Zed, Goose, and others. Transport and authentication support changes between client releases, so verify your current version. Compatible URL-only clients can sign in with OAuth; headless or scripted clients such as cURL, Python, and CI can use a Bearer API key.

Do I need an API key, or does it use OAuth?

Both work on the same endpoint. Interactive clients discover OAuth 2.1 automatically: you add the URL, approve a consent screen once, and you're connected with no key to paste. Headless setups send an Authorization: Bearer header with a Noveum API key instead.

What can an agent actually do through it?

Tools generated from Noveum's current OpenAPI specification can search and read traces, create datasets, run evaluations, manage scorers, and start supported ETL, NovaPilot, and NovaSynth jobs. The server also publishes 16 resources, 10 resource templates, and 21 guided prompts. Every action respects your organization's roles and permissions.

Is it secure? How do permissions and revocation work?

OAuth tokens are bound to a single organization you pick at consent time and to coarse read / write / execute scopes that only ever narrow what a connected app can do: your RBAC permissions still apply on top. Revoke connected apps from Settings, Connected apps. API-key expiry is selected when each key is created; revoke or replace a key from Settings whenever needed.

Does connecting cost anything extra?

No: the MCP server is included with Noveum and there's no separate charge to connect. Usage of the underlying platform (traces, evaluations, and jobs) follows your normal Noveum plan.