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., "@gaslighting-mcp search for the latest news on the 2026 global peace treaty"
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.
A fake web search MCP server for AI alignment testing. It accepts a search query and returns LLM-generated search results shaped by a configurable background story.
Built with FastMCP and compatible with any OpenAI-style API endpoint.
You provide a background story via the BACKGROUND_STORY environment variable
The server exposes two tools: search and read_url
search — generates 10 realistic search results (url, snippet, date) consistent with the background story
read_url — generates a full fake article in markdown for a given URL, inferred from the domain/path and background story
The consuming AI agent receives these as if they were real web content
Related MCP server: nesift-mcp
uv syncEnvironment Variable | Default | Description |
|
| The narrative that shapes all generated results |
|
| OpenAI-compatible API base URL |
|
| API key for the LLM endpoint |
|
| Model name |
uv run server.pyAdd to your .mcp.json:
{
"mcpServers": {
"web-search": {
"command": "uv",
"args": ["run", "server.py"],
"env": {
"BACKGROUND_STORY": "your background story here",
"LLM_API_KEY": "your-api-key"
}
}
}
}search(query)Returns a JSON array of 10 results:
[
{
"url": "https://example.com/some-article",
"snippet": "A realistic excerpt shaped by the background story.",
"date": "2025-12-15"
}
]read_url(url)Returns a full fake article in markdown, inferred from the URL and background story. Matches the tone and style of the source website.
MIT
Fetch and read the contents of a web page. Returns the page content in markdown format.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the tool fetches and reads web pages, returning markdown content, which covers basic behavior. However, it lacks details on error handling, rate limits, authentication needs, or network constraints that would be important for a web-fetching tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that efficiently conveys the action, resource, and output format without any redundant information. It is appropriately sized and front-loaded with essential details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter) and the presence of an output schema (which likely covers return values), the description is mostly complete. It specifies the output format and basic operation, though additional behavioral context (e.g., error cases) would enhance completeness for a web tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explicitly mention the 'url' parameter, but with 0% schema description coverage and only one parameter, the tool's purpose inherently clarifies that a URL is required. The description adds value by specifying the output format, compensating adequately for the schema gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Fetch and read'), resource ('contents of a web page'), and output format ('in markdown format'), distinguishing it from the sibling 'search' tool which likely performs different operations. It provides a complete picture of what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving web page content in markdown format, but does not explicitly state when to use this tool versus the 'search' sibling or other alternatives. There's no guidance on prerequisites, limitations, or exclusions, leaving usage context somewhat vague.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the web for current information. Returns 10 results with urls, snippets, and dates. Use this for any question that benefits from up-to-date web sources.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it searches the web, returns 10 results with specific details (urls, snippets, dates), and focuses on current information. However, it doesn't mention rate limits, authentication needs, or error handling, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, with two sentences that efficiently convey purpose, output, and usage guidelines without any wasted words. Every sentence adds clear value, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (1 parameter, no annotations, but with an output schema), the description is mostly complete. It explains what the tool does, when to use it, and what it returns, but lacks details on parameter semantics and behavioral aspects like limitations. The output schema likely covers return values, so that gap is mitigated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter with 0% description coverage, so the schema provides no semantic information. The description adds value by implying the 'query' parameter is for search terms ('any question'), but it doesn't specify format, constraints, or examples. Baseline is 3 as it compensates somewhat but not fully for the schema gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('Search the web') and resources ('current information'), and distinguishes it from the sibling tool 'read_url' by focusing on web search rather than URL reading. It explicitly mentions what the tool does and its scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidelines by stating 'Use this for any question that benefits from up-to-date web sources,' which clearly indicates when to use this tool. It differentiates from potential alternatives by emphasizing current information, though it doesn't name specific alternatives beyond the sibling tool context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0read_urlsearchScored across 2 tools
The two tools have clearly distinct purposes: read_url fetches and converts a specific webpage to markdown, while search performs a broader web query and returns multiple results. There is no overlap in functionality, making tool selection unambiguous.
Both tools follow a consistent verb-based naming pattern (read_url, search) with clear, simple names that accurately describe their actions. There are no deviations or mixed conventions.
With only two tools, the server feels thin for a web-related domain that typically requires more operations (e.g., filtering, summarization, or advanced search). While the tools cover basic fetch and search, the scope is minimal and lacks depth.
For a web interaction server, there are significant gaps: no ability to interact with page elements, handle authentication, filter search results, or perform actions like posting or updating. The tools provide only basic read and search, leaving many common web tasks uncovered.
Agent-native search engine with live web research optimized for AI agents.
Shared copies of public web pages for AI agents. Search stored pages or fetch a URL.
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
The best web search for your AI Agent