Add Agent47 - AI Agent Job Aggregator

[espadaw]

Adding Agent47, an MCP server that aggregates AI agent job opportunities from 9+ platforms including x402 Bazaar, RentAHuman, and Virtuals Protocol.

Features:

• Searches 1,680+ active jobs
• <200ms response time
• MCP 1.0 compatible
• Free during public beta

Summary by Sourcery

Add a new Agent47 MCP plugin providing unified AI agent job aggregation across multiple platforms.

New Features:

• Introduce the Agent47 MCP server integration with manifest configuration for SSE endpoint and capabilities to search, discover, and analyze AI agent jobs.
• Add user-facing README documenting installation, usage examples, features, pricing, and support links for the Agent47 job aggregator plugin.

Documentation:

• Document the Agent47 plugin, including supported platforms, capabilities, installation steps, usage example, feature overview, pricing, and external resources.

[sourcery-ai]

Reviewer's Guide

Adds a new MCP plugin "Agent47" that integrates an external AI agent job aggregator service by defining its manifest and providing plugin-specific documentation/usage instructions.

Sequence diagram for Agent47 MCP job search interaction

sequenceDiagram
    participant MCPClient
    participant MCPHost
    participant Agent47MCPServer
    participant JobPlatform_x402Bazaar
    participant JobPlatform_RentAHuman
    participant JobPlatform_VirtualsProtocol

    MCPClient->>MCPHost: callTool name findJobs category data_analysis minPrice 100 limit 10
    MCPHost->>Agent47MCPServer: SSE request to endpoint agent47_production_up_railway_app_sse
    Agent47MCPServer->>JobPlatform_x402Bazaar: fetch jobs category data_analysis minPrice 100
    Agent47MCPServer->>JobPlatform_RentAHuman: fetch jobs category data_analysis minPrice 100
    Agent47MCPServer->>JobPlatform_VirtualsProtocol: fetch jobs category data_analysis minPrice 100
    JobPlatform_x402Bazaar-->>Agent47MCPServer: job list
    JobPlatform_RentAHuman-->>Agent47MCPServer: job list
    JobPlatform_VirtualsProtocol-->>Agent47MCPServer: job list
    Agent47MCPServer-->>MCPHost: aggregated jobs limited to 10
    MCPHost-->>MCPClient: tool result jobs

Loading

Class diagram for Agent47 MCP manifest structure

classDiagram
    class Manifest {
        string identifier
        string name
        string version
        string description
        string author
        string homepage
        string repository
    }

    class McpConfig {
        string endpoint
        string protocol
        string transport
    }

    class Capability {
        string name
        string description
        string category
    }

    class Pricing {
        string model
        string future
    }

    class Support {
        string documentation
        string issues
        string status
    }

    Manifest --> McpConfig : has
    Manifest "1" --> "*" Capability : defines
    Manifest --> Pricing : uses
    Manifest --> Support : provides

    class Agent47PluginInstance {
        Manifest manifest
        McpConfig mcpConfig
        Capability capabilities
        Pricing pricing
        Support support
    }

    Agent47PluginInstance --> Manifest
    Agent47PluginInstance --> McpConfig
    Agent47PluginInstance --> Capability
    Agent47PluginInstance --> Pricing
    Agent47PluginInstance --> Support

Loading

File-Level Changes

Change	Details	Files
Introduce Agent47 MCP plugin documentation and usage guide.	Create README explaining what Agent47 does and which job platforms it aggregates. Document installation via npx and example JavaScript client usage against the SSE endpoint. Describe key features, pricing model, and provide external links for website, docs, status, and GitHub repo.	plugins/agent47/README.md
Register Agent47 plugin via MCP-compatible manifest pointing to the hosted SSE endpoint and exposed capabilities.	Define basic plugin metadata including identifier, name, version, description, author, homepage, and repository. Configure MCP connection details with SSE endpoint, protocol, and transport type. Declare available capabilities (findJobs, getTopOpportunities, comparePrice) with categories and descriptions for discovery. Add tags, pricing information, and support/documentation URLs for integration and troubleshooting.	plugins/agent47/manifest.json

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've left some high level feedback:

• The manifest’s pricing.future field is a free-form string; consider using a more structured shape (e.g., {"model": "pay-per-use", "currency": "USDC", "min": 0.001, "max": 0.005}) so downstream tooling can more reliably parse and surface pricing details.
• The README and manifest hard-code volatile metrics (job count, response time, uptime); consider either softening these claims or indicating they are approximate to avoid the need for frequent updates when the underlying numbers change.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The manifest’s `pricing.future` field is a free-form string; consider using a more structured shape (e.g., `{"model": "pay-per-use", "currency": "USDC", "min": 0.001, "max": 0.005}`) so downstream tooling can more reliably parse and surface pricing details.
- The README and manifest hard-code volatile metrics (job count, response time, uptime); consider either softening these claims or indicating they are approximate to avoid the need for frequent updates when the underlying numbers change.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}