MCP.so

Cala

Created By
3 months ago
Cala turns internet chaos into structured, verified knowledge that AI agents and LLMs can call as a tool. Building agentic products means relying on external information, but agents work best with verified, structured, typed data they can call deterministically, not the open web. Cala abstracts away ingestion, normalization, and verification behind a simple API, so you can ship agentic products faster without building brittle data pipelines.
OverviewContentToolsComments
Overview
- The Knowledge Layer for AI Agents","creator":{"@type":"Organization","name":"Mintlify","url":"https://mintlify.com"}})||!a.startsWith("lang:"))&&(localStorage.removeItem(a),l--)}document.documentElement.setAttribute(d,k?"visible":"hidden")}catch(a){console.error(a),document.documentElement.setAttribute(d,"hidden")}})(\n {},\n "en",\n [],\n "data-banner-state",\n "bannerDismissed",\n)","id":"_mintlify-banner-script"}])

} </style><style>:root { --primary: 52 45 42; --primary-light: 90 83 80; --primary-dark: 90 83 80; --tooltip-foreground: 255 255 255; --background-light: 255 255 255; --background-dark: 11 10 12; --gray-50: 244 244 244; --gray-100: 239 239 239; --gray-200: 224 223 223; --gray-300: 207 207 207; --gray-400: 160 159 159; --gray-500: 113 113 113; --gray-600: 81 81 81; --gray-700: 64 63 63; --gray-800: 38 38 38; --gray-900: 24 24 24; --gray-950: 11 11 11; }</style><div class="relative antialiased text-gray-500 dark:text-gray-400 [[&amp;_:is(h1,h2,h3,h4,h5,h6)]:font-headingsWeight [&amp;_*:not(h1,h2,h3,h4,h5,h6,h1_*,h2_*,h3_*,h4_*,h5_*,h6_*)]:font-bodyWeight"><script>(self.__next_s=self.__next_s||[]).push([0,{"suppressHydrationWarning":true,"children":"(function(a,b,c,d){var e;let f,g="mint"===d||"linden"===d?"sidebar":"sidebar-content",h=(e=d,f="navbar-transition","maple"===e&&(f+="-maple"),("willow"===e||"new-willow"===e)&&(f+="-willow"),f),[i,j]=(()=>{switch(d){case"almond":return["[--scroll-mt:2.5rem]","[--scroll-mt:2.5rem]"];case"luma":return["lg:[--scroll-mt:6rem]","lg:[--scroll-mt:6rem]"];case"sequoia":return["lg:[--scroll-mt:8.5rem]","lg:[--scroll-mt:11rem]"];default:return["lg:[--scroll-mt:9.5rem]","lg:[--scroll-mt:12rem]"]}})();function k(){document.documentElement.classList.add(i)}function l(a){document.getElementById(g)?.style.setProperty("top",${a}rem)}function m(a){document.getElementById(g)?.style.setProperty("height",calc(100vh - ${a}rem))}function n(a,b){!a&&b||a&&!b?(k(),document.documentElement.classList.remove(j)):a&&b&&(document.documentElement.classList.add(j),document.documentElement.classList.remove(i))}let o=document.documentElement.getAttribute("data-banner-state"),p=null!=o?"visible"===o:b;switch(d){case"mint":l(c),n(a,p);break;case"palm":case"aspen":case"sequoia":l(c),m(c),n(a,p);break;case"luma":k();break;case"linden":l(c),p&&k();break;case"almond":k(),l(c),m(c)}let q=function(){let a=document.createElement("style");return a.appendChild(document.createTextNode(",::before,::after{-webkit-transition:none!important;-moz-transition:none!important;-o-transition:none!important;-ms-transition:none!important;transition:none!important}")),document.head.appendChild(a),function(){window.getComputedStyle(document.body),setTimeout(()=>{document.head.removeChild(a)},1)}}();("requestAnimationFrame"in globalThis?requestAnimationFrame:setTimeout)(()=>{let a;a=!1,a=window.scrollY>50,document.getElementById(h)?.setAttribute("data-is-opaque",${!!a}),q()})})(\n false,\n false,\n (function m(a,b,c){let d=document.documentElement.getAttribute("data-banner-state"),e=2.5!!(null!=d?"visible"===d:b),f=3*!!a,g=4,h=e+g+f;switch(c){case"mint":case"palm":break;case"aspen":f=2.5*!!a,g=3.5,h=e+f+g;break;case"luma":g=3,h=e+g;break;case"linden":g=4,h=e+g;break;case"almond":g=3.5,h=e+g;break;case"sequoia":f=3*!!a,g=3,h=e+g+f}return h})(false, false, "mint"),\n "mint",\n)","id":"_mintlify-scroll-top-script"}])Skip to main content

("mint"===b||"linden"===b);if(g&&f)if(l>0){let a=Math.max(0,m-k);g.style.bottom=${l}px,g.style.top=${j-a}px}else g.style.bottom="",g.style.top=${a}rem,g.style.height="auto";i&&e&&(l>0?i.style.top="custom"===d?${e.clientHeight-l}px:${40+e.clientHeight-l}px:i.style.top="")})(\n (function m(a,b,c){let d=document.documentElement.getAttribute("data-banner-state"),e=2.5*!!(null!=d?"visible"===d:b),f=3*!!a,g=4,h=e+g+f;switch(c){case"mint":case"palm":break;case"aspen":f=2.5*!!a,g=3.5,h=e+f+g;break;case"luma":g=3,h=e+g;break;case"linden":g=4,h=e+g;break;case"almond":g=3.5,h=e+g;break;case"sequoia":f=3*!!a,g=3,h=e+g+f}return h})(false, false, "mint"),\n "mint",\n)","id":"_mintlify-footer-and-sidebar-scroll-script"}])
https://api.cala.ai/mcp/
For more information about MCP and how it works, you can read more about it here.

​
Connect your agent to Cala’s MCP

You can use Cala via our MCP. To get started, you need to get an API key to authenticate your MCP client. Go to our Console and create a new API key.

Get Cala's API key

Create a free Cala account and get your API key.
With your API key in hand, you can connect your AI agent such as Cursor, Claude Desktop and others to our MCP server. Cala MCP connects AI agents to our knowledge search, including verified, structured and typed knowledge, as well as entities information.
Add to ~/.cursor/mcp.json:
{
    "mcpServers": {
        "Cala": {
            "url": "https://api.cala.ai/mcp/",
            "headers": {
                "X-API-KEY": "YOUR_CALA_API_KEY"
            }
        }
    }
}
For more information, follow their documentation here.

​
Available Tools

Here are the tools available to the Cala MCP:

knowledge_search

Search for verified knowledge using natural language queries. Returns trustworthy, verified knowledge with relevant context and matching entities.

knowledge_query

Search for verified knowledge using structured query syntax such as: startups.location=Spain.funding>10M.funding<=50M. Returns a structured response with matching entities.

entity_search

Search entities by name with fuzzy matching.

entity_introspection

Get the field schema for an entity by its UUID. Returns the available properties, relationships, and numerical observations you can use when querying an entity.

get_entity

Get information about an entity by its UUID.
Try in Playground

Server Config

{
  "mcpServers": {
    "Cala": {
      "url": "https://api.cala.ai/mcp/",
      "headers": {
        "X-API-KEY": "YOUR_CALA_API_KEY"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
-
Star
-
Language
-
License
-
Category
Tags
Homepage
https://docs.cala.ai/integrations/mcp

Recommend Servers

View All
Agentladle/financial Reports

9 hours ago
SitePulsar
@SitePulsar

Agent Experience Optimization (AEO) audits over MCP — score how findable, readable, and usable your site is to AI agents across FIND/READ/USE, then get prioritized machine-actionable fixes.

a day ago
FiatDock
@FiatDock

Non-custodial USDC <-> bank for AI agents. Free quotes; $0.05 USDC per session via x402; 1% commission itemised in every quote. Own funds only. PT + EU/EEA (not UK). 18+.

11 hours ago
Github
@modelcontextprotocol

Repository management, file operations, and GitHub API integration

a year ago
Rinkta

Rinkta is a professional-services workspace for agencies and independent teams — tasks, projects, clients, and billable entries in one place. This connector lets your AI assistant search and read your workspace, look up tasks, projects, clients, and entries, and create new tasks and clients on your behalf. Access follows your workspace role: financial data (clients, projects, entries) is only visible to owners, admins, and accountants, and read-only connections never get write access.

15 hours ago
Blender
@ahujasid

BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

a year ago
Htmlbook
@htmlbook

A shelf for the HTML your AI coding agent writes. Push an HTML report, dashboard, or spec over MCP — htmlbook stores it, themes it for reading on any device, organizes it by project, and shares it with a link.

a day ago
Zhipu Web Search
@BigModel

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

a year ago
Feedjolt
@Feedjolt

Feedjolt's MCP server gives AI agents and MCP clients programmatic access to your feedback boards, posts, comments, roadmap, and changelog. Read feature requests, triage and tag feedback, change post statuses, merge duplicates, and publish changelog entries straight from any MCP-compatible client. Built for startups and indie teams who run their feedback loop where they build. Streamable-HTTP transport, API-key auth.

40 minutes ago
Redirhub Mcp Server
@redirhub

MCP server for RedirHub — AI-powered URL redirect management and link shortener. Create, update, test, and monitor redirects via Claude, Cursor, and any MCP client. Alternative to Bitly with custom domains and team collaboration.

3 hours ago
Unterm
@zhitongblog

The terminal AI agents can drive: a cross-platform desktop terminal (macOS/Linux/Windows, MIT) that runs a local MCP server. Spawn tabs/panes, run commands with structured output, read screens and full scrollback, take scrolling screenshots, record sessions with secret redaction, switch identity profiles. Auto-registers with Claude Code / Codex / Gemini CLI on install.

6 hours ago
Perplexity Ask MCP Server
@ppl-ai

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

JavaScript
a year ago
ParseBounce

ParseBounce is an email deliverability platform that tracks bounces, complaints and deliveries from AWS SES, SendGrid, Mailgun, SparkPost, Postmark and Mandrill. This MCP server connects Claude and other MCP clients to your ParseBounce projects: check whether an address is suppressed, investigate bounces and complaints, pull delivery/bounce/complaint rates, and look up crowdsourced email & domain reputation before you send. Search messages by recipient domain, campaign tracking ID, or full event timeline, and compare deliverability across time periods. You can also drive sending through the provider connected to your project — transactional emails and campaigns (create/pause/resume/cancel). Requires a ParseBounce account.

a day ago
Sellerguide

a day ago
AgentQL MCP Server
@tinyfish-io

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

JavaScript
a year ago
Polymarket Mcp Server
@Birantx

Polymarket prediction markets for Claude — market search, order books, price history, and a liquidity-rewards scanner. Credential-free.

17 hours ago
Agentladle Mcp/Financial Report
@achuan101

**AgentLadle** is a specialized Model Context Protocol (MCP) server designed for AI developers and platforms. By integrating this server, your AI assistants (like Claude) gain the superpower to instantly search, extract, and comprehend the **Annual Financial Reports (2023-2025)** of all listed companies in the **Chinese A-share market** (Shanghai and Shenzhen exchanges).

a day ago
Slipstack PDF
@Slipstack

Generate invoice and receipt PDFs from JSON. Agent-callable document API with a free demo quota — no install required. Hosted remote MCP server (streamable-HTTP) at https://slipstack.dev/api/mcp; a free demo quota of 10 documents/day per IP applies without an API key. Add an optional Bearer psk_ API key for plan quotas.

12 hours ago
Achivx Forum

43 minutes ago
GBOX Android MCP
@babelcloud

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

9 months ago
Autoresearch
@AIAgens

AutoSearch exposes a complete systematic-review pipeline as 6 MCP tools — not a thin search wrapper. `autosearch_run_research` launches an async PRISMA 2020 run (multi-source academic search across OpenAlex, Crossref, PubMed, Semantic Scholar, arXiv, ClinicalTrials.gov, DBLP and DOAJ; screening with recorded inclusion/exclusion decisions; evidence synthesis; IMRAD paper with APA references and PRISMA flow counts). Companion tools poll status, fetch the finished paper (markdown/JSON/PDF), verify any DOI live against Crossref, run one-shot evidence searches, and list runs. Citations are verified by construction: every DOI is checked against the Crossref API before it enters a deliverable, and a re-runnable citation-integrity benchmark is published at https://exatoshi.uk/trust (latest: 99/99 DOIs resolved, 0 fabricated, across 23 real deliverables — failures would be published too). Auth is a single `x-api-key` header; free account includes 50 credits. Docs with schemas, JSON examples and credit costs: https://exatoshi.uk/developers

13 hours ago
Giteasy
@greenmtnsun

When your AI runs git through a shell, it reads back raw command output — hundreds of tokens of noise to extract one piece of information. GitEasy MCP returns structured data: branch names, changed files, commit history — exactly what your AI needs, nothing extra. The same git operation at a fraction of the token cost. 21 tools, plain English, zero shell parsing.

11 hours ago
Firecrawl Mcp Server
@mendableai

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

JavaScript
a year ago
Cvforge
@mikelesagitter

a day ago
Mcp Emails

MCP Emails connects your email accounts (Gmail, Fastmail, generic IMAP/SMTP) to AI assistants. Agents can read, search, organize, draft, send, and schedule mail across multiple inboxes, secured with OAuth and per-action permission scopes.

21 hours ago
Howtocook Mcp
@worryzyy

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

a year ago
DocImprint
@Sawftware Labs

Verifiable document intelligence for AI agents. Extract, summarize, translate, claim-check, and notarize PDFs & URLs. Evidence bundles with cryptographic proofs and on-chain attestation. 20 MCP tools.

15 hours ago
Aiimagemultistyle
@codecraftm

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

a year ago
MCP Advisor
@istarwyh

MCP Advisor & Installation - Use the right MCP server for your needs

TypeScript
a year ago
Test
@modelcontextprotocol

test

6 months ago