tinyroe
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tinyroe fetch the contents of https://tinyfish.ai/blog as markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TinyRoe
TinyFish's two free tools, and nothing else.
The official TinyFish MCP server ships 19 tools plus a long instructions block, and six of them spend money. TinyRoe exposes only search and fetch_content, which TinyFish made free for every agent at any wallet balance, including $0.
It skips the OAuth too — these two are served over a REST API behind an X-API-Key header, so nothing expires and there is no authenticate stub to swap out. The same two tools are advertised always.
The project is TinyRoe; the package and the tool prefix are lowercase tinyroe.
tool | does | limit |
| web, news, or academic search | 30 requests/min |
| read up to 10 URLs, returns clean markdown | 150 URLs/min |
Install
Needs uv. No clone, no Node. Get a key at agent.tinyfish.ai/api-keys — it is shown once.
mkdir -p ~/.config/tinyroe
echo 'TINYFISH_API_KEY=your_key' > ~/.config/tinyroe/.envThen add the server:
claude mcp add tinyroe -s user -- uvx tinyroe # Claude Code, all projects
codex mcp add tinyroe -- uvx tinyroe # CodexOpenCode uses its own schema, in opencode.json or ~/.config/opencode/opencode.json:
{ "mcp": { "tinyroe": { "type": "local", "command": ["uvx", "tinyroe"], "enabled": true } } }Any other client takes the same two fields:
{ "mcpServers": { "tinyroe": { "command": "uvx", "args": ["tinyroe"] } } }Restart the client. You should see two tools and no authentication step.
Related MCP server: open-search-mcp
The key
TINYFISH_API_KEY in the environment wins, then ~/.config/tinyroe/.env, then a .env in the working directory. Prefer the config file: a client launched from a desktop app never sources your shell profile, so an export in .zshrc reaches terminal-launched clients only.
It is read lazily on the first call, so a missing key is a readable error rather than a server that will not start.
Development
uv sync
uv run ruff format . && uv run ruff check . && uv run basedpyright
uv run tinyroeLicence
MIT. Not affiliated with TinyFish; bring your own key.
Available Tools
2 toolsfetch_contentA
Read one or more URLs and return clean markdown. Free. Renders in a real browser, so JavaScript-heavy pages work. Up to 10 URLs, fetched in parallel. Prefer this over curl or raw HTTP for page content.
Inputs: urls (required), ttl, links, format, +3 more.
searchA
Web search. Free, fast, and the default way to ground an answer in current sources. Use before fetch_content when the right page is unknown. Returns ranked title/url/snippet lines.
Inputs: query (required), page, purpose, language, +9 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
Search discovers relevant URLs while fetch_content retrieves page content, making their roles complementary rather than overlapping. The description explicitly advises using search before fetch_content when the target page is unknown, further reducing ambiguity.
Both tool names are clear action-oriented verbs, though one is a bare verb (search) and the other follows a verb_noun pattern (fetch_content). This is a minor stylistic inconsistency rather than a functional or comprehension problem.
Two tools is borderline for a web research server, but the pair covers the essential search-then-fetch workflow compactly. The limited surface feels thin rather than bloated, and each tool earns its place.
The two tools form a complete core workflow: discover URLs via search and retrieve full content via fetch_content. Minor gaps exist, such as lacking search filters or page-level extraction options, but agents can accomplish the main research task without dead ends.
Maintenance
Related MCP Connectors
Web search API and MCP server for developers building AI agents.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Related MCP Servers
- AlicenseAqualityCmaintenanceA lightweight MCP server enabling web search and content fetching via TinyFish Free Access API with support for single and burst URL fetch.3MIT
- AlicenseAqualityDmaintenanceWeb search, page fetching, and research from the terminal or any MCP client — no API key required.31MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that provides web search scraping from DuckDuckGo (with Mojeek fallback) and URL content fetching as markdown/text or raw HTML.1ISC
- AlicenseAqualityCmaintenanceLocal MCP server for web search and page extraction, providing clean markdown from URLs, search results, site mapping, and research endpoints without API keys or accounts.5Apache 2.0