AgentGid

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Live data on AI agents, APIs and models: prices, free tiers, limits, outages, real-world usage.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AgentGid": {
      "url": "https://agentgid.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (22)

• find_tools read-only

  Search AgentGid for agents, coding tools, APIs, models and stacks that fit a goal, e.g. 'Solana LP copy-trading bot', 'web search API for a research agent under $50/month', 'animate a 2D game UI', 'free fonts for a mobile app'. Returns candidates grouped by kind (libraries and tools, content assets, agents, APIs, guides) with Gid Score, prices, licenses and links. Use this first, then get_tool / get_asset / get_api / get_agent for the full card.

  Parameters:

  • goal (required) — string — What the user wants to build or do, in plain words
  • limit — integer

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• list_api_categories read-only

  List the categories of APIs for agents AgentGid compares (web search, scraping, sandboxes, memory, vector DBs, LLM gateways, email, voice, payments, blockchain RPC, DEX swap, crypto data, 3D, image, audio, video generation).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• find_apis read-only

  Compare APIs in one category on official price, free tier, MCP support, SDK downloads and status. Filters are optional.

  Parameters:

  • category (required) — string — Category slug from list_api_categories, e.g. web-search, blockchain-rpc, 3d-generation
  • chain — string — For crypto APIs, e.g. Solana
  • mcp_only — boolean — Only APIs with an official MCP server
  • free_tier_only — boolean
  • max_price_per_1k — number — Max USD per 1,000 requests (only APIs with a per-request price)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_api read-only

  Full details of one API: pricing (free tier, plans, usage price, notes), SDK packages, MCP server, status, cheaper alternatives.

  Parameters:

  • api (required) — string — API slug or name, e.g. tavily, helius, meshy

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_agent read-only

  Details of an AI agent or developer tool (Claude Code, Cursor, Codex, Copilot, Headroom ...): pricing, plan usage limits, live status and incidents, latest release, popularity, safety settings.

  Parameters:

  • agent (required) — string — Agent slug or name

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• check_status read-only

  Live status of agents and APIs from their official status pages, with incidents in the last 30 days.

  Parameters:

  • names (required) — array

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• model_prices read-only

  API prices of LLMs (per 1M input/output tokens, context) and which agents can use them. Optional filter by name.

  Parameters:

  • limit — integer
  • query — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• real_world_usage read-only

  From public GitHub repos set up for AI coding agents: the MCP servers developers connect (overall or per agent), common combinations, and per domain (Solana bots, EVM apps, games, agent products, mobile) the APIs, SDKs and packages they use.

  Parameters:

  • agent — string — Optional: claude-code, cursor or github-copilot
  • domain — string — Optional: solana, evm, games, agent-apps, mobile — what those projects use

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• current_deals read-only

  Active official offers from the makers of AI agents and tools: discounts, free access, extra usage, credits, student, startup and open-source programs. Each comes from the vendor's own page, with its end date and source.

  Parameters:

  • kind — string — Optional: usage_boost, discount, free_access, credits, student, startup, open_source
  • agent — string — Optional: agent or vendor, e.g. claude-code, cursor, OpenRouter

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• limit_resets read-only

  When Anthropic and OpenAI last reset the 5-hour and weekly usage limits of Claude Code and Codex, how often they do it, and recent resets with a link to each announcement.

  Parameters:

  • product — string — Optional: claude-code or codex (default both)

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• price_history read-only

  How an agent's plans and prices changed month by month, read from archived copies of its official pricing page.

  Parameters:

  • agent (required) — string — Agent slug or name, e.g. cursor, claude-code

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• find_assets read-only

  Sources of UI kits and templates, fonts, icons, illustrations, colors, backgrounds, mockups, logos, placeholders, stock photos, video, music, voiceover and 3D for apps, websites and games: price, whether the license allows commercial use, needs credit, can ship inside an app or be fetched by bots, the rules to follow and how an agent connects (MCP, API, package, download). get_asset gives the full card with the license quotes.

  Parameters:

  • query — string — Optional words to match in the name or description
  • style — string — Optional look, e.g. minimal, flat, outline, hand-drawn, 3d, isometric, playful, corporate, colorful, pixel
  • category — string — Optional category, e.g. ui-kits, fonts, icons, illustrations, 3d-illustrations, color-palettes, backgrounds-patterns, mockups, logos, placeholders, favicons-og, stock-photos, music, voiceover, 3d-models
  • free_commercial_only — boolean — Only sources whose free plan allows commercial use

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• find_skills read-only

  Agent Skills packs (SKILL.md) for Claude Code, Codex, Cursor and other agents that read skills, from public GitHub repos: what the pack covers, number of skills, stars and the AgentGid page with install commands.

  Parameters:

  • query (required) — string — What the skills should help with, e.g. frontend design, pdf, testing
  • limit — integer

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_tool read-only

  The full AgentGid card of a library, framework or dev tool (React, GSAP, Zod, FastAPI, Phaser ...): install line, latest version, license and warnings, rules for AI agents (current API, what not to use), docs written for agents (llms.txt), Gid Score, downloads, use in projects built with AI agents, often-used-with and checked alternatives.

  Parameters:

  • tool (required) — string — Tool slug, name or package, e.g. gsap, framer-motion, pillow

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• design_recipe read-only

  A license-checked kit for one kind of site, picked from AgentGid's catalog: UI kit, fonts, icons, colors, art, logos, placeholders, favicon/OG tools, libraries and Agent Skills, plus a brief to paste into AGENTS.md. Recipes: minimal-saas-landing, playful-consumer-app, dashboard, creative-portfolio, docs-site. Call with no arguments to list them.

  Parameters:

  • style — string — Or a look, e.g. minimal, playful, gradient: the recipe whose styles match best
  • recipe — string — Recipe slug, e.g. minimal-saas-landing

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• product_recipe read-only

  The parts for one kind of AI product, picked from AgentGid's checked catalog: APIs per part (free tier, price, official MCP server and its card), the model per price tier, libraries, Agent Skills, coding agents, the cost to start and a brief to paste into AGENTS.md. Recipes: rag-assistant, voice-agent (with the cost of a call minute), ai-chatbot, support-agent, research-agent, telegram-ai-bot, data-analyst-agent, solana-bot, prompt-to-video. Call with no arguments to list them.

  Parameters:

  • recipe — string — Recipe slug or words, e.g. rag-assistant, voice agent, solana

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_asset read-only

  The full AgentGid card of a content source (Google Fonts, Kenney, Pixabay, ElevenLabs ...): price and free tier, every license term with the quote from the official license and its URL (commercial use, credit, inside an app, YouTube, AI training, bots), rules to follow, how to connect (MCP, API, package), lines to paste into a prompt.

  Parameters:

  • asset (required) — string — Asset source slug or name, e.g. google-fonts, kenney, poly-haven

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• find_resources read-only

  Remarkable websites a project can build on (live maps of planes, ships, weather and earthquakes, open data and statistics, book, map and art archives, space, science): whether there is an official API, whether it needs a key, whether the data can be downloaded, commercial use and embedding with quotes from the official pages, and build ideas. get_resource gives the full card.

  Parameters:

  • live — boolean — Only live (real-time) data
  • limit — integer
  • query — string — Words to match, e.g. earthquakes, public domain art, books, satellite
  • no_key — boolean — Only APIs that work without a key
  • category — string — Optional category name, e.g. Live planet, Books and libraries, Museums and art
  • free_api — boolean — Only resources with a free official API
  • commercial — boolean — Only resources whose license allows commercial use

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_resource read-only

  The full AgentGid card of a resource (USGS earthquakes, NASA images, Open Library, Met Museum ...): the official API with an example request, key and limits, data download, license with quotes, rules for agents and build ideas.

  Parameters:

  • resource (required) — string — Resource slug or name

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• list_recipes read-only

  List the project types AgentGid has a tested kit for (a 2D browser platformer, an interactive 3D web scene, a short-video pipeline, video and audio to text, a PDF tool...): id, title, the questions that shape the kit, and when it was test-built by a coding agent.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• plan_project read-only

  Get a project kit: one part per job from AgentGid's catalogs (with version, license and reasons), install lines, checks, and with files=true the AGENTS.md brief, CREDITS.md, first prompt and MCP setup files. Give a recipe id from list_recipes or the goal in plain words. If no recipe fits the goal, it says so and lists the recipes: it never improvises a stack.

  Parameters:

  • on — object — Switch parts on or off: {role id: true|false}. Optional parts start off. Assets, agent skills and MCP servers can be switched off, and the brief then says they were removed; parts the plan is built on (libraries, runtimes, services) can only be swapped through picks
  • add — array — Add up to 8 parts from AgentGid's catalogs that the recipe does not list: item ids such as "tool:pikepdf" or {"item": id, "stage": "agent|build|check|ship"}. They are checked against the answers like every part and marked as added in the files.
  • goal — string — What to build, in plain words, e.g. 'a Mario-style browser game'
  • files — boolean — Also return the texts of AGENTS.md, CREDITS.md, first-prompt.txt, install.txt and setup files
  • packs — object — Choose a pack, model or font inside a picked source: {role id: item id}
  • picks — object — Swap a part: {role id: item id}, ids as in a previous answer's parts[].pick and alternatives
  • prompt — string — First prompt: stop after each step (default) or run the whole plan
  • recipe — string — Recipe id from list_recipes, e.g. 2d-platformer
  • answers — object — Answers by question id, e.g. {"use": "commercial", "budget": "free", "agent": "cursor", "style": "pixel"}

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• report_kit_issue

  Tell AgentGid's editors what was wrong, missing or out of date in a kit's AGENTS.md after you built from it: a command that failed, a version that did not install, a step that did not work. Only the editors read it; it is never published. Leave out keys, personal data and the person's code.

  Parameters:

  • recipe (required) — string — The recipe id from the brief's first lines, e.g. mcp-server (a draft's id starts with draft-)
  • text (required) — string — What happened and where: the brief's line, the command and its output, and what worked instead
  • version — string — The recipe version from the same line, e.g. 0.3

  Hints: read-only no · destructive no · idempotent no · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.