"Steps for analyzing new API documentation and writing test cases" matching MCP servers:

Demo MCP server that exposes order and customer data as read-only tools for AI assistants, simulating a business API or internal data source.

Enables Claude Desktop to answer natural-language questions about customers by exposing search, profile, order history, status filter, and spend statistics tools backed by local mock data, with a single-file swap path to Oracle AI Agent Studio later.

Production-ready MCP server enabling AI assistants to interact with Braze's customer engagement platform, offering 92 tools for user management, messaging, campaigns, analytics, email/SMS, catalogs, and SCIM provisioning.

Enables AI agents to interact with Salesforce CRM data by executing SOQL queries and managing records. It provides tools for object metadata discovery and record operations, specifically optimized for Heroku deployment.

Enables AI assistants to query Salesforce data including retrieving accounts by ID, searching accounts by name, and fetching recent opportunities through authenticated API access.

Enables AI agents to perform comprehensive person and company lookups by integrating directly with the Lusha API for business contact enrichment. It provides tools for bulk contact identification via LinkedIn URLs, emails, or names, alongside detailed company information retrieval.

Enables interaction with mParticle's Data Planning API to manage data plans, retrieve schemas, and govern data workflows via natural language.

Enables AI assistants to interact with the Multilead platform for lead management, email campaigns, conversations, webhooks, and analytics through 74 API endpoints.

Provides comprehensive tools and resources for managing Klaviyo marketing automation, including profiles, lists, campaigns, flows, and more through natural language.

Enables an AI agent to fetch member profiles and generate deterministic, partner-rule-compliant travel recommendations on a multi-tenant white-label platform.

Enables asking questions in plain language to explore loyalty and promo data through Voucherify API endpoints.

Read-only, PII-masked MCP server for querying data federated through DuckDB — list sources/tables, inspect schemas, and run SQL across Postgres, MySQL, SQLite, Snowflake, BigQuery, Excel, and files, governed per source/table/column by a charter.yaml contract. Snowflake, BigQuery, Excel, and files, governed per source/table/column by a charter.yaml contract.

An MCP server that connects AI assistants like Claude, Cursor, and Windsurf to the Waitlister API. Create waitlists and manage subscribers through natural language.

Enables AI assistants to enrich contacts and build audiences via the YourICP API. Provides tools to set an API token, submit contact lookups by email or LinkedIn URL, and poll for enrichment results.

Enables AI agents to verify email addresses, clean lists, run bulk verification jobs, and manage a Verifly account through natural language, without writing HTTP calls.

LeadFuze MCP Server for contact/company enrichment from email or LinkedIn URL plus email validation. Hosted MCP endpoint: https://mcp.leadfuze.com/mcp (API key required).

MCP server for Postscript SMS marketing platform, enabling AI agents to query subscribers, look up opt-in keyword IDs, add new subscribers with consent, list campaigns, and check audience segment sizes.

An MCP server that enables AI assistants to interact with the CleverTap REST API to manage user profiles, events, campaigns, and reports. It supports multi-project configurations and provides tools for data analysis and campaign management through natural language.

A server for interacting with the Iaptic API, allowing AI models like Claude to query customer, purchase, and transaction data, as well as retrieve statistical insights.

Anchord MCP is a hosted remote MCP server for AI agents that need canonical identity resolution and safe write evaluation across customer systems. Resolve companies and people to canonical AnchorIDs, inspect linked records and target-system coverage, and evaluate whether a proposed write should be allowed or blocked. Read-only by design.