Fiddler MCP Server

The Fiddler MCP Server is in Public Preview. See Feature Maturity Definitions for what this means.

MCP tools run with your full account permissions: anything you can view or edit in Fiddler, a connected assistant can too. Because the external AI client controls tool execution, Fiddler is not responsible for actions taken by connected agents. Only authorize clients you trust and be intentional with your prompts.

Fiddler provides a Model Context Protocol (MCP) server that exposes your GenAI observability data to MCP-compatible AI assistants. Connect any MCP-compatible client and your AI assistant can explore applications, investigate traces, review evaluator results, monitor metrics, and more — without leaving the editor.

The Fiddler MCP Server is dramatically improved in release 26.16, and we’re actively expanding its capabilities. We’d love your feedback: share your thoughts and suggestions with support@fiddler.ai.

Prerequisites

A Fiddler account
Your Fiddler instance URL (e.g., https://your-instance.fiddler.ai)
An MCP client that supports remote HTTP MCP with OAuth 2.0, such as Claude Code or OpenCode. For other clients, see Limitations for the OAuth 2.0 redirect URL requirements.

Claude Desktop and Claude.ai are not currently supported due to a known issue in how those clients handle OAuth 2.0 authorization. We’re tracking this and will update this page once it’s resolved. See Limitations for client requirements.

Authentication

The Fiddler MCP Server authenticates with OAuth 2.0. On first connection, your client opens your browser to sign in through Fiddler and receives a short-lived token — you never paste a static key into a config file. The client then acts with your own account’s permissions, and standard role-based access control (RBAC) applies: a client can see and do only what your account is authorized to. Those permissions cover write actions too. Depending on your role, the tool catalog includes creating, modifying, and permanently deleting resources such as traces and sessions, and Fiddler does not add a confirmation step of its own before a tool runs. Most MCP clients ask for approval before executing tools; keeping that enabled for write actions is a good default.

Connect with OAuth 2.0

Fiddler composes the exact configuration for your deployment and shows it in the product. To connect your MCP client:

Open the MCP settings

In the Fiddler UI, go to Settings > MCP. The MCP Integration page shows a ready-to-use configuration for each supported client: select Claude Code, OpenCode, or Generic.

Copy the client configuration

Copy the command or config snippet shown for your client. For Claude Code this is a single terminal command; for OpenCode it is a JSON block for your opencode.jsonc. The snippet already contains your deployment’s OAuth 2.0 client ID, scopes, issuer, and MCP Server URL — see OAuth 2.0 client setup below for what each client expects.

Start your client and sign in

Start (or restart) your MCP client. On first connection, your browser opens to sign in through Fiddler. After you sign in, the client acts with your own account’s permissions and can begin querying your GenAI observability data.

Verify the connection

Ask the assistant something simple, such as “Show me my GenAI applications and give me a short summary of what’s there.” If your client lists the server’s tools, seeing just three (search_tools, describe_tools, execute_tool) is expected; the assistant uses them to discover and run Fiddler’s full tool catalog.

OAuth 2.0 Client Setup

Use the tab that matches your client. The Client ID, scopes, issuer, and redirect URLs are specific to your deployment — always copy the live values from Settings > MCP. The snippets below show the shape of each client’s configuration. Your client requests three OAuth 2.0 scopes:

openid — standard OpenID Connect scope; signs you in and identifies your account.
offline_access — issues a refresh token so your client can renew its short-lived access token without repeated sign-ins.
<project-audience-scope> — targets the token at Fiddler’s MCP resource server so it’s accepted. This value is specific to your deployment and is included in the config you copy.

Claude Code
OpenCode
Generic (other clients)

Run the command shown under Settings > MCP > Claude Code in your terminal. It registers the Fiddler MCP Server with its OAuth 2.0 details in one step:

claude mcp add-json fiddler-mcp '{
  "type": "http",
  "url": "https://<your-fiddler-url>/v1/mcp/genai/",
  "oauth": {
    "clientId": "<your-oauth-client-id>",
    "scopes": "openid offline_access <project-audience-scope>"
  }
}'

The first time an assistant uses the server, Claude Code opens your browser to sign in.

Add the following block to the "mcp" section of your opencode.jsonc file, then restart OpenCode. Copy the exact values from Settings > MCP > OpenCode:

"fiddler-mcp": {
  "enabled": true,
  "type": "remote",
  "url": "https://<your-fiddler-url>/v1/mcp/genai/",
  "oauth": {
    "clientId": "<your-oauth-client-id>",
    "scope": "openid offline_access <project-audience-scope>"
  }
}

OpenCode opens your browser to sign in on first connection.

For any other OAuth 2.0-capable client, configure the connection manually using the values from Settings > MCP > Generic:

Parameter	Description	Example
Client ID	The OAuth 2.0 client identifier your MCP client authenticates with.	`<your-oauth-client-id>`
Scopes	Space-separated OAuth 2.0 scopes requested during authentication.	`openid offline_access <project-audience-scope>`
MCP Server URL	The Fiddler MCP endpoint your client connects to.	`https://<your-fiddler-url>/v1/mcp/genai/`
Issuer	The OAuth 2.0 issuer (authorization server) that issues tokens.	`https://<your-issuer-url>`

Your client must use one of Fiddler’s pre-registered OAuth 2.0 redirect URLs; see Limitations for the supported callback paths.Refer to your client’s documentation for how to configure a remote MCP Server with OAuth 2.0.

Disconnect a Client

To disconnect a client, remove the Fiddler MCP Server from its configuration:

Claude Code — run claude mcp remove fiddler-mcp.
OpenCode — delete the fiddler-mcp block from your opencode.jsonc.
Other clients — remove the Fiddler MCP Server entry as described in your client’s documentation.

Removing the configuration stops that client from connecting to Fiddler again. Credentials the client already obtained remain valid until they expire: by default, access tokens expire within one hour and refresh tokens within 24 hours. A refresh token also expires after 2 hours 24 minutes without use — even if its 24-hour absolute lifetime has not elapsed — so an idle client must sign in again. Deployments with custom token policies may differ.

Recommended Models

MCP provides tools to an agent, but the results are only as good as the agent and model using them: the model decides which tools to call, how to chain them, and how to interpret what comes back. Smaller and faster model tiers can struggle with the multi-step tool use that observability questions often require, so we recommend the following minimums from each major provider:

Provider	Minimum recommended model
Anthropic	Claude Sonnet (Sonnet 4.5 or newer)
OpenAI	GPT-5
Google	Gemini 2.5 Pro

A few additional considerations:

For data analysis work, such as asking questions over large volumes of trace and span data, prefer higher-tier models with large context windows.
Agents can make mistakes when condensing large amounts of information, so spot-check important conclusions against the Fiddler UI.
For other providers or open-weight models, choose a tier similar or stronger to those listed above, with solid tool-calling support.

Using MCP

There is no special syntax to learn: ask in plain language and the assistant uses Fiddler’s tools to answer your questions. The tools support creating, viewing, updating, and deleting information in Fiddler, so an assistant can both answer questions and make changes on your behalf. Below are the tool domains covered and some example prompts you can use to get started.

Projects & Apps

“Tell me about my most active applications and what the most active agents we are observing are.”“Tell me about my Customer Support app: its health, recent traffic, and which evaluators are running on it.”

Traces & Sessions

“Find a recent session in my Customer Support app and walk me through what happened: what was asked, what the agents did, and how it ended.”“Search my Customer Support app for spans that mention payment failures and tell me which sessions they belong to.”

Evaluators & Rules

“Which evaluators are running on my Customer Support app?”“Help me set up sentiment scoring evaluators on my Customer Support app.”“Let’s look at results from my sentiment evaluator and help me iterate: test improved prompts against sample responses, then update the evaluator once the scores look right.”

Charts & Dashboards

“Create a chart tracking p95 latency over the last 7 days for my Customer Support app.”“What does the dashboard for my Customer Support app show right now? Tell me what charts are on it.”

Metrics

“What’s the average number of input tokens per LLM call in my Customer Support app?”“Create a custom metric that tracks average input tokens per LLM call, then chart it over the last 7 days.”

Evals Datasets & Experiments

“What evals datasets and experiments does my Customer Support app have, and how did the latest experiment score?”“Show me the five worst rows of the latest experiment by answer similarity, with each row’s input and score.”

Alerts

“What alert rules are configured on my Customer Support app?”“Set up an alert that notifies me if traffic to my Customer Support app drops to zero.”

LLM Gateway

“Which LLM providers and models are configured in my gateway?”“What model options are available for each provider I’ve configured?”

Attributes & Annotations

“Which LLM models show up in my Customer Support app’s traffic?”“List the chart annotations in my project and tell me if any line up with last week’s latency spike.”

Backfills

“Did the historical evaluator run on my Customer Support app finish? Are there any failed tasks I should worry about?”“Score last month’s traffic with my secret detection evaluator: backfill the last 30 days.”

Limitations

GenAI and agentic tools only — ML model monitoring features are not available through MCP.
Trace content truncation — long trace content may be truncated by default to manage context window usage; ask your assistant to fetch a specific span in full if you need to inspect its complete content.
No Dynamic Client Registration — Fiddler does not implement OAuth 2.0 Dynamic Client Registration (DCR), so MCP clients must be pre-registered and use a pre-registered redirect URL for the OAuth 2.0 callback. The supported redirect URLs are:
- http://127.0.0.1/mcp/oauth/callback
- http://127.0.0.1/callback
Since these use the loopback IP literal (127.0.0.1) without a fixed port, a single entry covers any ephemeral local port your client picks. If your client uses a different callback path, contact Fiddler Support to add it. Clients that can only register via DCR — with no way to configure a pre-registered client ID — cannot connect today. The MCP specification has deprecated DCR in favor of Client ID Metadata Documents (CIMD), which Fiddler is evaluating.
Claude Desktop and Claude.ai — not currently supported due to a known issue in how those clients handle OAuth 2.0 authorization; we’re tracking this and will update this page once it’s resolved.
Rate limiting — requests to the MCP Server are rate-limited at 120 requests per minute per connected client by default. Exceeding the limit returns a 429 response with a Retry-After header.

What’s Next?

Agentic AI Overview — Browse all Fiddler integrations for agentic AI
Fiddler OTel SDK — Instrument custom Python agents with OpenTelemetry
Fiddler Evals SDK — Run offline evaluations on your LLM applications
Agentic AI Observability — Complete setup guide for GenAI monitoring

Agentic AI & LLM Frameworks

Data Platforms & Pipelines

ML Platforms & Tools

Cloud Platforms & Deployment

Monitoring & Alerting

Prerequisites

Authentication

Connect with OAuth 2.0

OAuth 2.0 Client Setup

Disconnect a Client

Recommended Models

Using MCP

Projects & Apps

Traces & Sessions

Evaluators & Rules

Charts & Dashboards

Metrics

Evals Datasets & Experiments

Alerts

LLM Gateway

Attributes & Annotations

Backfills

Limitations

What’s Next?

​Prerequisites

​Authentication

​Connect with OAuth 2.0

​OAuth 2.0 Client Setup

​Disconnect a Client

​Recommended Models

​Using MCP

Projects & Apps

Traces & Sessions

Evaluators & Rules

Charts & Dashboards

Metrics

Evals Datasets & Experiments

Alerts

LLM Gateway

Attributes & Annotations

Backfills

​Limitations

​What’s Next?

Prerequisites

Authentication

Connect with OAuth 2.0

OAuth 2.0 Client Setup

Disconnect a Client

Recommended Models

Using MCP

Limitations

What’s Next?