History

Ajax Davis 5c9f1a1d0a chore: update dependencies with compatibility fixes - Update all packages to latest versions via pnpm update --latest - Downgrade Prisma 7 to 6 (v7 requires schema migration) - Downgrade Tailwind CSS 4 to 3 (v4 requires PostCSS migration) - Downgrade Storybook 10 to 8 (addons not available in v10) - Pin cheerio to 1.0.0-rc.12 via pnpm override (type exports changed) - Fix AI SDK tool definitions: parameters -> inputSchema - Fix cheerio types in extract-meta and table-extract tools - Add explicit type annotations to tool execute functions - Migrate biome config to v2.3.11 schema All type-checks, tests, and builds pass.		2026-01-09 22:49:41 +10:00
..
src	refactor: rename exportName to name across entire codebase	2025-12-17 17:19:21 +10:00
CHANGELOG.md	chore: version packages for release	2025-12-12 09:50:42 +10:00
package.json	chore: update dependencies with compatibility fixes	2026-01-09 22:49:41 +10:00
README.md	docs(sdk): add API keys documentation section	2025-12-12 11:35:51 +10:00
tsconfig.json	feat: add @tpmjs/registrySearch and @tpmjs/registryExecute SDK packages	2025-12-12 07:29:06 +10:00

README.md

@tpmjs/registry-search

Search the TPMJS tool registry from any AI SDK agent. Discover thousands of tools dynamically.

Installation

npm install @tpmjs/registry-search
# or
pnpm add @tpmjs/registry-search

Usage

import { streamText } from 'ai';
import { anthropic } from '@ai-sdk/anthropic';
import { registrySearchTool } from '@tpmjs/registry-search';
import { registryExecuteTool } from '@tpmjs/registry-execute';

const result = streamText({
  model: anthropic('claude-sonnet-4-20250514'),
  tools: {
    registrySearch: registrySearchTool,
    registryExecute: registryExecuteTool,
  },
  system: `You have access to the TPMJS tool registry.
Use registrySearch to find tools, then registryExecute to run them.`,
  prompt: 'Search for web scraping tools and scrape https://example.com',
});

// The agent can now:
// 1. Search for tools: registrySearch({ query: "web scraping" })
// 2. Execute found tools: registryExecute({ toolId: "@firecrawl/ai-sdk::scrapeTool", params: { url: "..." } })

Tool: registrySearchTool

Search the TPMJS registry to find AI SDK tools.

Parameters

Name	Type	Required	Description
`query`	string	Yes	Search query (keywords, tool names, descriptions)
`category`	string	No	Filter by category
`limit`	number	No	Max results (1-20, default 5)

Returns

{
  "query": "web scraping",
  "matchCount": 3,
  "tools": [
    {
      "toolId": "@firecrawl/ai-sdk::scrapeTool",
      "name": "scrapeTool",
      "package": "@firecrawl/ai-sdk",
      "description": "Scrape any website into clean markdown",
      "category": "web-scraping",
      "requiredEnvVars": ["FIRECRAWL_API_KEY"],
      "healthStatus": "HEALTHY",
      "qualityScore": 0.9
    }
  ]
}

Understanding `requiredEnvVars`

The requiredEnvVars field tells you which API keys a tool needs to function. When executing a tool with @tpmjs/registry-execute, pass these keys in the env parameter:

// 1. Search finds a tool that needs FIRECRAWL_API_KEY
const searchResult = await registrySearchTool.execute({ query: 'web scraping' });
// searchResult.tools[0].requiredEnvVars = ["FIRECRAWL_API_KEY"]

// 2. Execute the tool with the required key
const result = await registryExecuteTool.execute({
  toolId: '@firecrawl/ai-sdk::scrapeTool',
  params: { url: 'https://example.com' },
  env: { FIRECRAWL_API_KEY: 'fc-xxx' }  // Pass required keys here
});

Tools with an empty requiredEnvVars array don't need any API keys.

Environment Variables

Variable	Default	Description
`TPMJS_API_URL`	`https://tpmjs.com`	Base URL for the registry API

Self-Hosted Registry

To use your own TPMJS registry:

export TPMJS_API_URL=https://registry.mycompany.com

@tpmjs/registry-execute - Execute tools found with this package
TPMJS Registry - Browse all available tools

License

MIT