Skip to content
Back to search

mcp-omnisearch

πŸ” A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/spences10/mcp-omnisearch with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/spences10/mcp-omnisearch'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/spences10--mcp-omnisearch/badge.svg)](/listings/spences10--mcp-omnisearch)

HTML

<a href="/listings/spences10--mcp-omnisearch"><img src="/api/listings/spences10--mcp-omnisearch/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install the published server with [MCPick](https://github.com/spences10/mcpick):

npx mcpick add \
  --name mcp-omnisearch \
  --command npx \
  --args=-y,mcp-omnisearch

MCPick defaults to Claude Code. Use `--client` and `--scope` to target another client or add the server to the current repository:

npx mcpick add \
  --name mcp-omnisearch \
  --command npx \
  --args=-y,mcp-omnisearch \
  --client vscode \
  --scope project

See [Deployment](docs/deployment.md#install-with-mcpick) for supported clients and provider credential storage options.

To run from source instead:

pnpm install
pnpm run build
node ./dist/index.js

Providers without keys are skipped and the rest keep working. If your client supports environment-variable expansion, reference keys instead of storing their values in the MCP configuration:

{
	"mcpServers": {
		"mcp-omnisearch": {
			"command": "npx",
			"args": ["-y", "mcp-omnisearch"],
			"env": {
				"TAVILY_API_KEY": "${TAVILY_API_KEY}",
				"EXA_API_KEY": "${EXA_API_KEY}"
			}
		}
	}
}

Add only the provider keys you use. Expansion syntax and secret storage are client-specific; see [Deployment](docs/deployment.md#keep-provider-keys-out-of-mcp-configuration) for secure options and plaintext fallback guidance.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md Β· README Β· 170 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # mcp-omnisearch
  2. [![built with vite+](https://img.shields.io/badge/built%20with-Vite+-646CFF?logo=vite&logoColor=white)](https://viteplus.dev)
  3. [![tested with vitest](https://img.shields.io/badge/tested%20with-Vitest-6E9F18?logo=vitest&logoColor=white)](https://vitest.dev)
  4. A Model Context Protocol (MCP) server for Tavily, Brave, Kagi, Exa,
  5. GitHub, Linkup, and Firecrawl. Two tools, `search` and `execute`,
  6. expose schema-generated native provider functions through Pi's local
  7. QuickJS sandbox. Requires Node.js 22.19+.
  8. <a href="https://glama.ai/mcp/servers/gz5wgmptd8">
  9. <img width="380" height="200" src="https://glama.ai/mcp/servers/gz5wgmptd8/badge" alt="Glama badge" />
  10. </a>
  11. ## Quick start
  12. Install the published server with
  13. [MCPick](https://github.com/spences10/mcpick):
  14. ```bash
  15. npx mcpick add \
  16. --name mcp-omnisearch \
  17. --command npx \
  18. --args=-y,mcp-omnisearch
  19. ```
  20. MCPick defaults to Claude Code. Use `--client` and `--scope` to target
  21. another client or add the server to the current repository:
  22. ```bash
  23. npx mcpick add \
  24. --name mcp-omnisearch \
  25. --command npx \
  26. --args=-y,mcp-omnisearch \
  27. --client vscode \
  28. --scope project
  29. ```
  30. See
  31. [Deployment](https://github.com/spences10/mcp-omnisearch/blob/main/docs/deployment.md#install-with-mcpick)
  32. for supported clients and provider credential storage options.
  33. To run from source instead:
  34. ```bash
  35. pnpm install
  36. pnpm run build
  37. node ./dist/index.js
  38. ```
  39. Providers without keys are skipped and the rest keep working. If your
  40. client supports environment-variable expansion, reference keys instead
  41. of storing their values in the MCP configuration:
  42. ```json
  43. {
  44. "mcpServers": {
  45. "mcp-omnisearch": {
  46. "command": "npx",
  47. "args": ["-y", "mcp-omnisearch"],
  48. "env": {
  49. "TAVILY_API_KEY": "${TAVILY_API_KEY}",
  50. "EXA_API_KEY": "${EXA_API_KEY}"
  51. }
  52. }
  53. }
  54. }
  55. ```
  56. Add only the provider keys you use. Expansion syntax and secret
  57. storage are client-specific; see
  58. [Deployment](https://github.com/spences10/mcp-omnisearch/blob/main/docs/deployment.md#keep-provider-keys-out-of-mcp-configuration)
  59. for secure options and plaintext fallback guidance.
  60. ## Tools
  61. ### `search`
  62. Discover available functions and their compact TypeScript
  63. declarations. A provider-scoped lookup returns names and schemas
  64. together:
  65. ```json
  66. { "query": "tavily" }
  67. ```
  68. Use an exact name such as `tavily_search` for a smaller lookup, or
  69. `{}` for a catalog without declarations. Only configured providers
  70. appear.
  71. ### `execute`
  72. Run JavaScript against the discovered native provider functions:
  73. ```json
  74. {
  75. "code": "const r = await tools.tavily_search({ query: 'MCP code mode', max_results: 3 }); return r.results.map(({ title, url }) => ({ title, url }));"
  76. }
  77. ```
  78. Compose calls with `await` and `Promise.all`, filter intermediate
  79. data, and return only what the client needs. Credentials stay on the
  80. host; the sandbox has no filesystem or arbitrary network access.
  81. Arguments and responses use native provider formats, not a normalized
  82. search contract. See
  83. [Code Mode](https://github.com/spences10/mcp-omnisearch/blob/main/docs/codemode.md)
  84. for functions, limits and benchmark findings.
  85. ## Upgrading
  86. The consolidated `web_search`, `ai_search`, `web_extract` and
  87. `github_search` tools have been removed. Provider keys stay the same,
  88. but existing tool calls and client instructions need migration. See
  89. the
  90. [breaking-change migration guide](https://github.com/spences10/mcp-omnisearch/blob/main/docs/migration.md).
  91. ## Documentation
  92. - [Migration](https://github.com/spences10/mcp-omnisearch/blob/main/docs/migration.md)
  93. β€” move from consolidated tools to Code Mode.
  94. - [Code Mode](https://github.com/spences10/mcp-omnisearch/blob/main/docs/codemode.md)
  95. β€” native provider functions, schema generation, local testing, and
  96. benchmark findings.
  97. - [Provider selection](https://github.com/spences10/mcp-omnisearch/blob/main/docs/provider-selection.md)
  98. β€” choose providers by task, key, mode, and capability.
  99. - [Search operators](https://github.com/spences10/mcp-omnisearch/blob/main/docs/search-operators.md)
  100. β€” native query syntax and provider-specific filters.
  101. - [Large results](https://github.com/spences10/mcp-omnisearch/blob/main/docs/large-results.md)
  102. β€” inline vs file response behavior and remote deployment caveats.
  103. - [Deployment](https://github.com/spences10/mcp-omnisearch/blob/main/docs/deployment.md)
  104. β€” MCP client, WSL, and Firecrawl setup.
  105. - [Troubleshooting](https://github.com/spences10/mcp-omnisearch/blob/main/docs/troubleshooting.md)
  106. β€” keys, access, validation, rate limits, and common failures.
  107. ## Environment variables
  108. - `TAVILY_API_KEY`
  109. - `KAGI_API_KEY`
  110. - `BRAVE_API_KEY`
  111. - `GITHUB_API_KEY`
  112. - `EXA_API_KEY`
  113. - `LINKUP_API_KEY`
  114. - `FIRECRAWL_API_KEY`
  115. - `FIRECRAWL_BASE_URL` optional, for self-hosted Firecrawl
  116. - `OMNISEARCH_LARGE_RESULT_MODE` optional, `file` default or `inline`
  117. ## Development
  118. ```bash
  119. pnpm install
  120. pnpm run build
  121. pnpm test
  122. ```
  123. Please read
  124. [CONTRIBUTING.md](https://github.com/spences10/mcp-omnisearch/blob/main/CONTRIBUTING.md)
  125. before opening a PR.
  126. ## License
  127. MIT License - see
  128. [LICENSE](https://github.com/spences10/mcp-omnisearch/blob/main/LICENSE).
  129. ## Acknowledgments
  130. Built on
  131. [Model Context Protocol](https://github.com/modelcontextprotocol),
  132. [Tavily](https://tavily.com), [Kagi](https://kagi.com),
  133. [Brave Search](https://search.brave.com), [Exa AI](https://exa.ai),
  134. [Linkup](https://linkup.so), and [Firecrawl](https://firecrawl.dev).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.