HridaSpro Docs

MCP Server

Connect the Spro docs MCP server to Claude.ai, ChatGPT, Claude Code, Codex, Cursor, VS Code and other MCP clients, so your agent can search and read the current Spro docs.

The Spro docs are available as a Model Context Protocol (MCP) server. Connect it to your AI tool and the agent can search every page of the docs and read the exact section it needs, so its answers about Spro come from the current docs instead of memory.

The server is:

  • Read-only. It only reads the public docs. It cannot change your account, keys or data.
  • Open. It needs no API key and no sign-in.
  • Current. It serves the same pages the website publishes, so limits, endpoints and model names stay up to date.

Server URL

Server URL
https://spro.hridaai.com/mcp

Use this URL exactly, with no trailing slash. It uses the Streamable HTTP transport.

Name the server spro-docs in your client so it is easy to recognize. The examples below use that name.

Quick start

Copy this into your AI agent

Paste this into your coding agent (Claude Code, Cursor, Codex CLI, and others). It detects which client you use and sets up the server:

Prompt for your AI agent
Connect the Spro docs MCP server to my coding agent so it can look up current Spro docs and API details.
Server to add:- `spro-docs`: https://spro.hridaai.com/mcp
Detect which agent or editor I am using (Claude Code, Cursor, Codex CLI, Claude Desktop, Deep Agents Code, VS Code, Antigravity, or another MCP-compatible client) and use the matching setup from https://spro.hridaai.com/docs/mcp:
- Claude Code: `claude mcp add --transport http spro-docs https://spro.hridaai.com/mcp` (project scope by default; use `--scope user` only if I ask for global access).- Codex CLI: `codex mcp add spro-docs --url https://spro.hridaai.com/mcp`.- Cursor, Deep Agents Code, VS Code, or Antigravity: add the `spro-docs` entry to the MCP settings JSON, using the field names shown on that page for my client.- Claude Desktop: add https://spro.hridaai.com/mcp under Settings > Connectors.- Claude.ai or ChatGPT on the web: add it as a custom connector in the app settings, as described on that page.
Do not invent alternate MCP URLs. After configuring, confirm that `spro-docs` is listed and reachable, and that it exposes the tools about_spro, search_docs, get_doc and list_docs.

Claude Code

Run this in your project directory to add the server to that project:

Claude Code: this project
claude mcp add --transport http spro-docs https://spro.hridaai.com/mcp

To make it available in every project, add --scope user:

Claude Code: all projects
claude mcp add --transport http spro-docs --scope user https://spro.hridaai.com/mcp

Codex

Run this to add the server:

Codex
codex mcp add spro-docs --url https://spro.hridaai.com/mcp

Claude.ai (web)

  1. Go to Customize > Connectors at claude.ai/customize/connectors.
  2. Click + and choose Add custom connector.
  3. Enter a name, for example Spro Docs, and the URL https://spro.hridaai.com/mcp.
  4. Leave the advanced OAuth fields empty. The server needs no authentication.
  5. Click Add, then turn the connector on in the chat where you want to use it.

Note

Plans and organizations. The free plan allows one custom connector. On Team and Enterprise, an organization owner adds the connector under Organization settings > Connectors, and members connect it from their own Customize > Connectors page.

ChatGPT (web)

  1. Go to Settings > Connectors > Advanced settings and turn on Developer mode. This depends on your ChatGPT plan.
  2. Go back to Connectors and click Create.
  3. Enter a name, for example Spro Docs, and the URL https://spro.hridaai.com/mcp.
  4. Set authentication to No authentication, tick the trust checkbox, then click Create.
  5. In a new chat, open the + menu, choose More, select Developer mode, and turn on Spro Docs.

Note

ChatGPT's menu names and plan rules change. If a label differs, check OpenAI's help center.

Other clients

Claude Desktop

  1. Open Claude Desktop.
  2. Go to Settings > Connectors.
  3. Add https://spro.hridaai.com/mcp.

Cursor

Add this to .cursor/mcp.json in a project, or to ~/.cursor/mcp.json for all projects:

.cursor/mcp.json
{  "mcpServers": {    "spro-docs": {      "url": "https://spro.hridaai.com/mcp"    }  }}

VS Code

Add this to .vscode/mcp.json in your workspace:

.vscode/mcp.json
{  "servers": {    "spro-docs": {      "url": "https://spro.hridaai.com/mcp"    }  }}

Deep Agents Code

Add this to ~/.deepagents/.mcp.json for every project, or to a project's .mcp.json for one project:

~/.deepagents/.mcp.json
{  "mcpServers": {    "spro-docs": {      "type": "http",      "url": "https://spro.hridaai.com/mcp"    }  }}

Restart dcode to load the server. In an interactive session, run /mcp to check its status and tools.

Antigravity

Add this to your MCP settings file:

Antigravity MCP settings
{  "mcpServers": {    "spro-docs": {      "serverUrl": "https://spro.hridaai.com/mcp"    }  }}

Any other MCP client

Any client that supports remote MCP over Streamable HTTP can connect to https://spro.hridaai.com/mcp. No headers or authentication are needed.

Tools

The server exposes four read-only tools.

ToolArgumentsWhat it returns
search_docsquery (required), limit (optional, default 5, max 20)The best-matching sections across all docs. Each result has the page title, section heading, path, URL and a snippet. Typos and partial words still match.
get_docpath (required)The full Markdown of one page, for example routing/strategies. Add #section-anchor to get only one section, for example routing/strategies#fallback-chains-you-send-yourself. If the path is wrong, the response suggests close matches.
list_docsnoneEvery page with its path, title and description.
about_sprononeA short overview of Spro and where to start.

A typical agent calls search_docs to find the right section, then get_doc to read it in full.

Search covers every section of every page, including the API reference, cookbook, guides and FAQs. When a query contains a misspelling, the response lists the correction it used, so you can see how the match was made.

Check that it works

Start a new session in your client and ask a question about Spro that the docs answer, for example:

How do I turn on Flex pricing for a request?

The agent should call search_docs, then get_doc, and answer from the Flex page with a link to it.

To check the server from a terminal, send a tools/list request:

Check the server from a terminal
curl -s -X POST https://spro.hridaai.com/mcp \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -H "MCP-Protocol-Version: 2025-06-18" \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

The response lists about_spro, list_docs, search_docs and get_doc.

What to ask

  • "Which Spro service tier is cheapest for a background job, and what are its trade-offs?"
  • "How do I make Spro cache semantically similar questions?"
  • "Show me how to send a fallback chain of models through Spro."
  • "What does Zero Data Retention store and what doesn't it?"
  • "Which alerts should I turn on for a new workspace?"

Troubleshooting

The client doesn't show the server or its tools. Check that the URL is exactly https://spro.hridaai.com/mcp, with no trailing slash. Then restart the client or start a new session, since most clients load MCP servers at startup.

Opening the URL in a browser shows JSON. That is expected. The URL is for MCP clients. The response is a description of the server: its name, instructions, and tools. To read the docs, use the website.

The agent answers without calling the tools. Ask it to use the spro-docs tools explicitly, for example "Search the Spro docs for Flex pricing." If it still doesn't call them, confirm the server is listed as connected in your client's MCP or connectors settings.

An answer looks outdated. Ask the agent to call get_doc on the page and quote the relevant section. Then compare it with the page on the website, and tell the Spro team if they differ.

Other ways to read the docs

  • Add .md to any docs URL to read that page as Markdown, for example https://spro.hridaai.com/docs/integrations/http.md.
  • llms.txt has a short summary and links to the main sources.
  • llms-full.txt has the full question-and-answer reference.

Learn more