TPC Benchmarks

Can an agent use this product?

See whether an AI coding agent can actually integrate a developer API, SDK or tool from its documentation, measured by The Prompting Company. Ask about a product or a category, such as search APIs or transactional email, and get measured results in chat: completion rate, passed, failed and blocked runs, average successful run time, and an overall score from 0 to 100 that averages an experience score (graded on Install, Auth, Execute, Docs and Current) and an agent readiness score.

What you can ask

Compare agent onboarding benchmark results for search APIs.
Example path →

MCP connector

Server URL: https://benchmarks.promptingcompany.com/mcp
Login: None
Protocol: MCP 2025-11-25
Instructions: Measured, independent data on developer APIs, SDKs and tools for AI agents: for each product, whether a real AI coding agent could go from the product's docs to a first successful integration, with completion rate, blocked runs, run time and an overall score. Use when the user asks about measured integration or onboarding results for a developer API, SDK or tool, or asks to choose between or compare such products. Use when the user wants to see the results as cards. Use when the user asks how a product's score has trended or changed over time, or when the client cannot render the cards. Use only when the user asks to have a product benchmarked or added; it records a request for the TPC team and changes no results. Benchmarked categories: Email (tasks: Create and delete an inbox; Read delivery and bounce events; Send a transactional email), Search (tasks: Make a web search request; Scrape a URL to markdown; Search and return result excerpts), Weather API.

Tools

Reads data3

Changes data2

Skills

None in the store listings or on the server

MCP connector

Server URL

https://benchmarks.promptingcompany.com/mcp

None

Protocol

MCP 2025-11-25

Instructions

Measured, independent data on developer APIs, SDKs and tools for AI agents: for each product, whether a real AI coding agent could go from the product's docs to a first successful integration, with completion rate, blocked runs, run time and an overall score. Use when the user asks about measured integration or onboarding results for a developer API, SDK or tool, or asks to choose between or compare such products. Use when the user wants to see the results as cards. Use when the user asks how a product's score has trended or changed over time, or when the client cannot render the cards. Use only when the user asks to have a product benchmarked or added; it records a request for the TPC team and changes no results. Benchmarked categories: Email (tasks: Create and delete an inbox; Read delivery and bounce events; Send a transactional email), Search (tasks: Make a web search request; Scrape a URL to markdown; Search and return result excerpts), Weather API.