Connect Informatica to Claude: Manage Governance and Data Catalogs

If your team uses ChatGPT, check out our guide on connecting Informatica to ChatGPT or explore our broader architectural overview on connecting Informatica to AI Agents.

Giving a Large Language Model (LLM) read and write access to a sprawling data governance ecosystem like Informatica is a significant engineering challenge. You must handle complex session-based authentication lifecycles, map massive JSON schemas to tool definitions, and deal with Informatica's strict API quotas. Every time Informatica updates an endpoint or introduces a new API version, you have to update your server code, redeploy, and test the integration.

To connect Informatica to Claude to automate data catalogs, manage governance rules, or oversee taskflows, you need a Model Context Protocol (MCP) server. This server acts as the translation layer between Claude's tool calls and Informatica's REST APIs. You can either build and maintain this infrastructure yourself, or use a managed integration platform like Truto to dynamically generate a secure, authenticated MCP server URL.

This guide breaks down exactly how to use Truto to generate a secure, managed MCP server for Informatica, connect it natively to Claude Desktop, and execute complex workflows using natural language.

The Engineering Reality of the Informatica API

A custom MCP server is a self-hosted integration layer. While the open MCP standard provides a predictable way for models to discover tools, the reality of implementing it against specialized enterprise APIs is painful. Informatica Intelligent Cloud Services (IICS) is built to manage massive data pipelines, strict governance, and complex access controls. Its API reflects that immense complexity.

If you decide to build a custom Informatica MCP server, here are the specific integration challenges you will face:

Fragmented API Versions and Domains Informatica is not a single API. It is a collection of microservices. You have the Platform REST API v2 for legacy tasks, the Platform REST API v3 for newer objects, the Data Governance and Catalog API, and the Data Profiling API. An LLM has no context on which API version or domain to use for a given task. You must build an abstraction layer that presents a unified set of operations to Claude, hiding the underlying endpoint fragmentation.

Complex Session-Based Authentication Unlike modern APIs that accept a static Bearer token, Informatica often requires a two-step authentication dance. You must first hit a login endpoint (/public/core/v3/login) to exchange credentials for a temporary session ID and an organization-specific base URL. This session ID must be passed in a specialized header (e.g., INFA-SESSION-ID) for subsequent requests, and it expires. Your custom MCP server would need to manage this token lifecycle, refreshing it dynamically before it drops mid-session. Truto's managed infrastructure handles this session lifecycle entirely behind the scenes.

Asynchronous Jobs and Multipart File Handling Many operations in Informatica are not synchronous CRUD. Operations like migrating assets require creating an export job, polling for completion, downloading a ZIP package, and uploading that ZIP package to a target environment using multipart/form-data. Instructing an LLM to navigate a multi-step, asynchronous polling loop while handling binary file buffers is nearly impossible without strictly structured, curated tools.

Rate Limiting Realities Informatica enforces strict rate limits to protect its multi-tenant infrastructure. Factual note on rate limits: Truto does not retry, throttle, or apply backoff on rate limit errors. When the upstream Informatica API returns an HTTP 429, Truto passes that error directly to the caller. Truto normalizes upstream rate limit info into standardized headers (ratelimit-limit, ratelimit-remaining, ratelimit-reset) per the IETF spec. The caller (your LLM agent or framework) is completely responsible for handling retry and backoff logic. Do not expect the MCP server to magically absorb rate limit errors.

Step 1: Generating the Informatica MCP Server

Truto dynamically generates MCP tools based on documentation and API schemas. A tool only appears in the MCP server if it has a corresponding documentation entry - this acts as a quality gate to ensure Claude only sees well-documented endpoints.

You can generate the MCP server URL through the Truto dashboard or programmatically via the API.

Method A: Via the Truto UI

This is the fastest path for one-off internal workflows.

1. Log in to your Truto dashboard and navigate to the Integrated Accounts page.
2. Select your connected Informatica account.
3. Click the MCP Servers tab.
4. Click Create MCP Server.
5. Select your desired configuration (e.g., restrict to read methods only, or filter by specific tool tags like governance).
6. Copy the generated MCP server URL (it will look like https://api.truto.one/mcp/<secure-token>).

Method B: Via the Truto API

For teams building multi-tenant AI applications, you will want to generate these servers programmatically. Truto provides a REST endpoint to create an MCP server linked to a specific integrated account.

Endpoint: POST /integrated-account/:id/mcp

// Example: Generating an Informatica MCP server restricted to read operations
const response = await fetch('https://api.truto.one/integrated-account/infa_abc123/mcp', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_TRUTO_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    name: "Informatica Governance AI Agent",
    config: {
      methods: ["read", "list"], // Restrict Claude to read-only access
      tags: ["governance", "catalog"]
    },
    expires_at: "2026-12-31T23:59:59Z" // Auto-revoke access at year-end
  })
});
 
const data = await response.json();
console.log(data.url); // https://api.truto.one/mcp/a1b2c3d4...

The returned URL is self-contained. It encodes the specific Informatica tenant, the tool filters, and the expiration metadata.

Step 2: Connecting the MCP Server to Claude

Once you have the Truto MCP URL, you can plug it directly into your AI environment. All communication happens over HTTP POST with JSON-RPC 2.0 messages.

Method A: Via the Claude UI

If you are using Claude Desktop, Claude for Web, or ChatGPT (in Developer Mode), adding the server is a UI-driven process.

For Claude:

1. Open Claude Settings -> Integrations (or Connectors, depending on your tier).
2. Click Add MCP Server.
3. Paste the Truto MCP URL.
4. Click Add.

For ChatGPT:

1. Open ChatGPT Settings -> Apps -> Advanced settings.
2. Enable Developer mode.
3. Under MCP servers / Custom connectors, click add.
4. Name it "Informatica (Truto)" and paste the Truto MCP URL.
5. Click Save.

The LLM client will immediately perform a handshake, call tools/list, and discover all available Informatica operations.

Method B: Via Manual Config File

For custom agent frameworks or headless Claude Desktop deployments, you can configure the MCP server using standard Server-Sent Events (SSE) via the official MCP SDK.

Update your claude_desktop_config.json (or equivalent configuration):

{
  "mcpServers": {
    "informatica-truto": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sse",
        "--url",
        "https://api.truto.one/mcp/YOUR_SECURE_TOKEN"
      ]
    }
  }
}

Because Truto dynamically flattens the input namespace, your AI agent will automatically separate query parameters and body payloads based on the schemas provided by the tools/list response.

Hero Tools for Informatica

Truto maps Informatica's complex API surface into hundreds of discrete MCP tools. Below are the highest-leverage tools for automating data governance, job monitoring, and source control.

list_all_informatica_objects

Find assets (projects, folders, mappings, tasks, taskflows, connections) across the organization using the platform REST API v3. This tool is essential for agent discovery, allowing the LLM to locate specific asset IDs needed for downstream operations.

"Claude, search our Informatica environment for all mapping tasks where the location is 'Production' and the type is 'MTT'. Return their asset IDs."

get_single_informatica_catalog_job_by_id

Retrieve the job run details for Data Governance and Catalog jobs (such as catalog source jobs, import jobs, and export jobs). Because Informatica relies heavily on async polling, this tool allows Claude to verify if a long-running data catalog scan has finished.

"Check the status of catalog source job ID 8f72b-11a. If it has completed, let me know how many records were processed."

list_all_informatica_data_asset_profiles

Retrieve data profiles configured for a specific data set via the Data Governance API. This tool gives Claude visibility into how data quality is being measured across your organization.

"List all the data asset profiles configured for the 'Customer_Master_V2' dataset. I need to know which profiling rules are currently active."

informatica_taskflow_runs_resume_with_retry

Resume a suspended taskflow run by retrying the faulted step. This is a powerful automated remediation tool. When combined with alerts, Claude can investigate a failed pipeline and attempt an intelligent restart without human intervention.

"Taskflow run ID 992-abc is currently in a suspended state. Please trigger a resume with retry on the faulted step."

informatica_source_control_pull

Pull the latest versions of objects from the source control repository into the Informatica organization. This tool bridges DevOps and data engineering, allowing Claude to deploy mapping updates directly from a Git repository.

"Pull the latest commits from our source control repository into the Informatica staging environment."

get_single_informatica_profile_run_by_id

Retrieve the detailed results of a data profiling job run. Claude can use this data to perform advanced analysis on data quality, identifying null patterns, datatype mismatches, or unexpected value frequencies.

"Get the details for data profile run ID 4432. Summarize any anomalies detected in the inferred datatypes or column value frequencies."

To view the complete inventory of Informatica tools and their exact JSON schemas, visit the Informatica integration page.

Workflows in Action

Connecting tools to an LLM is only the first step. The true power of MCP emerges when Claude chains these tools together to execute complex, multi-step workflows. Here are real-world examples of how data engineering teams use this integration.

Workflow 1: Automated Taskflow Debugging and Remediation

Data pipelines fail. Instead of a data engineer logging into the IICS portal, checking logs, and manually retrying a task, Claude can handle the triage.

"Check our Informatica environment for any taskflow runs that are currently suspended. If you find one, get its details, tell me what step failed, and attempt to resume it with a retry."

Execution Steps:

1. Claude calls list_all_informatica_taskflow_runs with a filter for status=='suspended'. It identifies a failed run (ID: tf-881).
2. Claude calls get_single_informatica_taskflow_run_by_id passing tf-881 to investigate the failure payload and identify the faulted step.
3. Claude calls informatica_taskflow_runs_resume_with_retry to trigger a restart.

Result: The LLM triages the pipeline failure, communicates the root cause back to the user in plain text, and safely triggers a retry - cutting resolution time from minutes to seconds.

Workflow 2: Data Governance Profiling Audit

Data stewards need to constantly monitor data quality. Claude can automate the extraction and summarization of Data Profiling results.

"Find the data profile for our 'EMEA_Sales' dataset. Run a new profile task for it, wait for it to complete, and summarize the top column value frequencies."

Execution Steps:

1. Claude calls list_all_informatica_data_asset_profiles searching for 'EMEA_Sales' to retrieve the Profile ID.
2. Claude calls informatica_data_asset_profiles_run using that ID to trigger a new profiling job.
3. (Claude knows to wait or instructs the user to wait) Claude calls get_single_informatica_data_asset_profile_run_by_id to check the status.
4. Once complete, Claude calls list_all_informatica_profile_column_value_frequencies to extract the statistical data and summarize it.

Result: The user receives a clean, conversational summary of the dataset's current health, outliers, and value distributions without writing any SQL or clicking through the Informatica UI.

sequenceDiagram
    participant User as User
    participant Claude as Claude
    participant Truto as Truto MCP
    participant Informatica as Informatica API

    User->>Claude: "Run profile for EMEA_Sales and summarize results"
    Claude->>Truto: Call list_all_informatica_data_asset_profiles
    Truto->>Informatica: GET /data-governance/profiles
    Informatica-->>Truto: Return Profile ID
    Truto-->>Claude: Profile ID: 5543
    Claude->>Truto: Call informatica_data_asset_profiles_run
    Truto->>Informatica: POST /data-governance/profiles/5543/run
    Informatica-->>Truto: Run ID: 998
    Truto-->>Claude: Job started
    Claude->>Truto: Call list_all_informatica_profile_column_value_frequencies
    Truto->>Informatica: GET /data-profiling/frequencies
    Informatica-->>Truto: Frequency Data
    Truto-->>Claude: JSON stats
    Claude-->>User: "The profile is complete. Top frequencies..."

Security and Access Control

Exposing an enterprise platform like Informatica to an AI agent requires strict guardrails. Truto's MCP architecture provides several layers of security to ensure agents only execute authorized actions.

• Method Filtering: You can restrict the MCP server token to specific operational categories using config.methods. Passing ["read"] ensures the LLM can only execute get and list operations, entirely preventing accidental deletions or modifications.
• Tag Filtering: Use config.tags to limit the exposed tools to specific domains. For example, filtering by ["governance"] will hide all platform configuration or user provisioning tools, exposing only data catalog tools.
• API Token Authentication: By default, the MCP server URL acts as a bearer token. By enabling require_api_token_auth: true, Truto forces the connecting client to also pass a valid Truto session or API token, ensuring the URL cannot be abused if leaked.
• Automatic Expiration: You can set an expires_at ISO datetime when creating the MCP server. Truto relies on cloud infrastructure to automatically revoke the token and clean up the database record once the TTL expires, making it perfect for temporary contractor access or limited-time audit workflows.

Strategic Wrap-up

Connecting Claude to Informatica transforms how data engineering and governance teams interact with their infrastructure. Instead of wrestling with complex XML payloads, two-step session authentication, and asynchronous polling loops, teams can use natural language to orchestrate deployments, debug taskflows, and extract data governance insights.

Building this integration in-house means owning the technical debt of Informatica's API versioning, rate limiting, and schema management. By leveraging a managed MCP architecture, you offload the infrastructure maintenance and get back to building intelligent agent workflows.

Ready to scale your AI agent connectivity? Explore how Truto handles integration infrastructure securely.