Webhound

ai.webhoundPublished by webhound.aiOfficial publisherv0.5.2Updated Oct 24, 2026

Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Webhound gives an assistant a budgeted research harness that produces reports and datasets on demand.

What you can do
Webhound exposes a research harness built on DeepSeek V4 Pro and GPT-5.4, referred to as Hound. According to the registry description, it produces budgeted reports and datasets. The manifest lists no individual tools, so the exact operations are not documented here.
When to use it
Consider it when an assistant needs to generate research reports or datasets and you want spending to be bounded by a budget. It is less clearly useful if you need a documented, tool-by-tool view of capabilities before installing.
Requirements
A Webhound account and API key supplied as the WEBHOUND_KEY environment variable; OAuth authentication is declared as required. It can run as a remote endpoint at api.webhound.ai over streamable HTTP, or locally via the npm package webhound-mcp with npx over stdio. Network access is needed.
Before you install
The server requires a secret, WEBHOUND_KEY, and OAuth authentication, so treat the key as sensitive. The description mentions budgeted reports, which implies research work may incur costs against a budget; confirm pricing and limits before use. No tool list is published, so what it reads, writes, or sends to third parties is not verifiable from this listing.

Installation

In SourceWeft

  1. Open Webhound in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.webhound%2Fwebhound/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "webhound": {
      "type": "http",
      "url": "https://api.webhound.ai/api/v2/mcp"
    }
  }
}

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.5.2LatestSep 16, 2026

Score

60% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.