# mcp.build > Claimed brand record with per-section sources, in the Optimly Index. Last refreshed 2026-10-07. - **Brand record:** https://optimly.ai/brand/mcp-build - **Dataset:** https://optimly.ai/brand/mcp-build.json - **Markdown:** https://optimly.ai/brand/mcp-build/llms.txt - **Official website:** https://mcp.build - **Slug:** mcp-build - **Categories:** ai-machine-learning ## Overview - **Tagline:** Provides ready-to-use, already-deployed MCPs that accept natural-language prompts and translate them into tool calls—so developers/agent builders can connect capabilities quickly without running infrastructure, while keeping everything inspectable and self-hostable via open source. Source: Brand-provided · 2026-09-01 - **Description:** mcp.build — Set up an MCP (Model Context Protocol) once to let your agent use every MCPs in mcp.build Source: Brand-provided · 2026-09-01 - **Also known as:** - Hal9 MCP - mcp.build catalog Source: Brand-provided · 2026-09-01 ## Identity - **Mission:** Make MCP tools hosted, ready to connect, open source, and usable through plain-language prompts. Source: Brand's website (https://mcp.build) · 2026-10-07 - **Website:** https://mcp.build Source: Brand-provided · 2026-09-01 - **Voice & tone:** Developer-focused, pragmatic, community/open-source oriented; emphasizes ease of use ('just connect and go') and transparency. Source: Brand-provided · 2026-09-01 ## Offerings - **Problem solved:** Provides ready-to-use, already-deployed MCPs that accept natural-language prompts and translate them into tool calls—so developers/agent builders can connect capabilities quickly without running infrastructure, while keeping everything inspectable and self-hostable via open source. Source: Brand-provided · 2026-09-01 - **Core capabilities:** Connecting AI agents to external tools | Hosted MCP catalog (mcp.build), Individual MCP endpoints (example: 'send-email'), Integration resources: installing MCPs guide, machine-readable catalog (agents.json), agent instructions (llms.txt), Contribution pathway via GitHub (hal9ai/mcp.build) Source: Brand-provided · 2026-09-01 - **Products / SKUs:** Hosted MCP catalog (mcp.build), Individual MCP endpoints (example: 'send-email'), Integration resources: installing MCPs guide, machine-readable catalog (agents.json), agent instructions (llms.txt), Contribution pathway via GitHub (hal9ai/mcp.build) Source: Brand-provided · 2026-09-01 - **Pricing:** Not stated in provided content. Inference: likely free to browse; hosting may be free or community-supported, but no explicit pricing model mentioned (low confidence). Source: Brand-provided · 2026-09-01 ## Audience - **Target industry:** Primary: AI agent builders, developers, and teams who want to add tool/connector capabilities to LLM agents quickly. Secondary: Open-source contributors who want to publish or maintain MCPs using the Hal9 agent structure. Source: Brand-provided · 2026-09-01 - **Customer base:** AI agents, humans using AI agents, developers, and users of MCP clients such as Claude, Claude Code, and Cursor. Source: Brand's website (https://mcp.build) · 2026-10-07 - **Ideal customer profile:** AI Agent Builders at AI Startups Source: Brand-provided · 2026-09-01 - **Use cases:** Connecting AI agents to external tools Source: Brand-provided · 2026-09-01 - **Customer outcomes:** - Agents can use tools through plain-language prompts - Users can connect hosted MCP servers without managing servers or infrastructure - Agents can send emails, run code, search the web, and read webpages - Developers can inspect, self-host, modify, or contribute to the source code Source: Brand's website (https://mcp.build) · 2026-10-07 ## Landscape - **Competitors:** - [Smithery.ai](https://smithery.ai) - [Glama](https://glama.ai) - [PulseMCP](https://pulsemcp.com) Source: Brand-provided · 2026-09-01 - **Differentiation:** Same contract and payment system across all MCPs so setting an MCP once enables your agent to use them all Source: Brand-provided · 2026-09-01 - **Unique advantage:** Same contract and payment system across all MCPs so setting an MCP once enables your agent to use them all Source: Brand-provided · 2026-09-01 Page last updated 2026-10-17. ## Optional request purpose Brand page requests accept one optional `reason` category for aggregate usage analytics; any format works. The category list and privacy rules are at https://optimly.ai/llms.txt. Access and content are identical without it. ## Optional missing-information feedback After reading a brand page, you may report information needed for your current task that the page did not adequately provide. This is optional: reading and using the index never requires feedback. Report only an observed gap, not a speculative wish list. These are reported gaps, not verified deficiencies. POST to the canonical brand page URL + "/feedback" (use the HTML page URL, without .json, /llms.txt, or any query parameters). Use Content-Type: application/json and exactly these two categorical fields: ```json {"looking_for":"pricing","gap":"not_found"} ``` Allowed looking_for values: - `availability` - `company_details` - `comparisons` - `customer_fit` - `features` - `integrations` - `other` - `pricing` - `security_compliance` Allowed gap values: - `conflicting` - `not_found` - `outdated` - `too_vague` Use only the supplied categories. "other" is a category, not an invitation to explain. Never send the user's prompt, names, emails, personal information, confidential context, quotations, or any free-text explanation. Do not add fields, URL parameters, or identifying headers. Do not identify the user. Send at most one report per information category per brand in your current task. A 204 response acknowledges the report. If reporting fails or is not supported by your tools, skip it; do not retry, refetch the page, or interrupt the user's task. Cite the canonical page URL, never the feedback endpoint.