gpt-researcher-mcp
Integrates with Google's generative AI (Gemini) to enable automated web research, summarization, and structured report generation.
Click on "Install 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., "@gpt-researcher-mcpresearch the impact of remote work on productivity"
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.
gpt-researcher-mcp MCP server
A MCP server for gpt-researcher
This is just a MCP wrapper for gpt-researcher.
This project, gpt-researcher-mcp, is a wrapper extension built on top of the open-source project gpt-researcher. The original gpt-researcher was developed by Assaf Elovic, and I am not the original author.
gpt-researcher is an automated research assistant that performs web searches, summarizes information, and generates structured reports based on a given query. This wrapper (gpt-researcher-mcp) is designed to make the original tool more suitable for integration into MCP or similar workflows.
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
"gpt-researcher-mcp": {
"command": "npx",
"args": ["-y", "gpt-researcher-mcp"],
"env": {
"llm_provider": "google_genai",
"GOOGLE_API_KEY": "your key",
"FAST_LLM": "google_genai:gemini-1.5-flash",
"SMART_LLM": "google_genai:gemini-1.5-pro",
"STRATEGIC_LLM":"google_genai:gemini-1.5-pro",
"EMBEDDING": "google_genai:models/text-embedding-004",
"TAVILY_API_KEY": "your key"
}
}Related MCP server: Gemini Research MCP Server
Development
To prepare the package for distribution:
Sync dependencies and update lockfile:
uv syncBuild package distributions:
uv buildThis will create source and wheel distributions in the dist/ directory.
Publish to PyPI:
uv publishNote: You'll need to set PyPI credentials via environment variables or command flags:
Token:
--tokenorUV_PUBLISH_TOKENOr username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv run gpt-researcher-mcpUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Available Tools
2 toolsadd-noteC
Add a new note
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| content | Yes |
TDQS
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 only says 'Add a new note' and provides no details on side effects, permissions, return values, or error behavior.
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 short sentence with no wasted words, making it concise and front-loaded. However, it is under-specified for the tool's complexity, though this is largely a completeness issue rather than a conciseness issue.
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 lack of annotations, output schema, and parameter descriptions, a five-word description is insufficient for an agent to invoke the tool correctly. The meaning of the parameters and expected return behavior remain ambiguous.
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 zero description coverage for the two required parameters ('name' and 'content'), and the description does not explain their meaning or format. The agent cannot infer what 'name' or 'content' represent.
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 uses a specific verb ('Add') and a specific resource ('note'), clearly stating the tool's function. It differentiates itself from the sibling 'get_report', which is a read operation.
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?
No guidance is provided on when to use this tool versus alternatives. The description only states the action without any context about when to invoke it or when to choose a sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_reportC
Get a research report based on a query and report type
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| report_type | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden for behavioral disclosure. It only says 'get' a report, which implies a read operation, but it does not disclose potential side effects, permission requirements, rate limits, or what the return value contains. The lack of any additional behavioral context makes this inadequate for a tool with zero annotation coverage.
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, concise sentence that directly states the tool's purpose. Every word contributes to the core message, with no fluff or redundancy. It is front-loaded and efficiently sized for its minimal content.
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 there is no output schema and no annotations, the description should explain what constitutes a report, what the return format is, and how the parameters affect the result. It does none of these. The tool is simple (2 parameters), but the description leaves significant gaps in understanding the tool's behavior and expected inputs.
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?
Schema description coverage is 0%, and the input schema only gives parameter names and types. The description adds little beyond restating the parameter names: 'based on a query and report type' provides minimal context but no detail on valid formats, allowed values, dependencies, or defaults. It does not compensate for the missing schema descriptions.
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 gets a report, with a specific verb and resource, and mentions the two inputs (query and report type). It does not explicitly differentiate from the only sibling 'add-note', but the difference is obvious: one adds notes, the other gets reports. This is clear enough for a 4 but not a 5 due to lack of explicit sibling distinction.
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 gives no guidance on when to use this tool versus alternatives, no exclusions, and no context about prerequisite conditions or limitations. It simply states what it does, leaving the agent no direction on when it is the appropriate choice over other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
The two tools, add-note and get_report, have completely distinct purposes with no overlap. An agent can easily tell them apart based on their names and descriptions.
Both tool names follow a consistent verb_noun pattern using hyphens (add-note, get-report). This is a clear and predictable naming convention.
With only two tools, the server feels thin and borderline under-scoped for a research-focused MCP server. Two tools fall into the lower end of acceptable range but do not feel entirely insufficient.
The server lacks core operations for a research workflow, such as initiating research, listing past reports, or managing notes beyond adding. Significant gaps exist that would likely cause agent failures in practical use.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server for Google search results via SERP API
MCP server exposing the Backtest360 engine API as tools for AI agents.
Scrape, crawl and search the web for AI agents via MCP.
Related MCP Servers
- AlicenseAqualityDmaintenanceA deep-research MCP server exposing a single task-augmented tool that runs GPT-Researcher with Tavily search, Anthropic Claude, and OpenAI embeddings, streaming progress via MCP tasks and Upjack entity stream.7MIT
- AlicenseAqualityBmaintenanceMCP server for AI-powered research using Gemini. Provides fast grounded web search, deep autonomous research, URL extraction, and session management.69MIT
- AlicenseAqualityAmaintenanceAn MCP server that exposes Gemini's Deep Research Agent for comprehensive web research.21984MIT
- AlicenseNot gradedqualityAmaintenanceA self-contained web-research MCP server that lets local LLM agents search, fetch, and synthesize web content using tools like web_search, web_fetch, and web_research.1MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/markchiang/gpt-researcher-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server