Edmunds MCP server for AI agents

Let Claude, ChatGPT or your own agent read Edmunds: 5 typed functions through one MCP server. No Edmunds API key needed.

Functions
5
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just Edmunds

An MCP server for Edmunds alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.

https://api.bowmark.ai/mcp/site/edmunds
Every site

One MCP server for Edmunds and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.

Functions

Open a function to see its arguments, what it returns and how to call it.

Read 5
  • getDiscussionReads one Edmunds forum thread by discussion id, with its newest comments.

    Arguments

    NameTypeRequired
    discussionIdnumberYes
    commentLimitnumberNo

    Returns EdmundsDiscussion

    interface EdmundsComment { commentId: number; author: string | null; body: string; dateInserted: string | null; url: string }
    
    interface EdmundsDiscussion { discussionId: number; title: string; body: string; url: string; categoryId: number | null; author: string | null; dateInserted: string | null; dateLastComment: string | null; countComments: number; countViews: number; closed: boolean; tags: string[]; comments: EdmundsComment[] }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/edmunds/getDiscussion

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.edmunds.getDiscussion({ discussionId: 74237, commentLimit: 5 });
  • listCarModelsLists the car models the Edmunds forums know for a make (e.g. honda), with forum tag and category ids.

    Arguments

    NameTypeRequired
    makestringYes

    Returns EdmundsCarModel[]

    interface EdmundsCarModel { carModelId: number; makeId: number; id: string; name: string; niceName: string; categoryId: number | null; tagId: number | null; fullName: string }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/edmunds/listCarModels

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.edmunds.listCarModels({ make: "honda" });
  • listForumTagsLists or searches Edmunds forum tags (car makes, car models, user topic tags) with discussion counts.

    Arguments

    NameTypeRequired
    querystringNo
    type"CarMake" | "CarModel" | "User"No
    limitnumberNo

    Returns EdmundsForumTag[]

    interface EdmundsForumTag { tagId: number; name: string; type: string; urlcode: string; url: string; parentTagId: number | null; countDiscussions: number; numPosts: number; dateInserted: string | null }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/edmunds/listForumTags

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.edmunds.listForumTags({ query: "honda" });
  • searchForumPostsQuick search of Edmunds forum posts and comments, returning the top matches with author and thread id.

    Arguments

    NameTypeRequired
    termstringYes

    Returns EdmundsForumPost[]

    interface EdmundsBreadcrumb { name: string; url: string }
    
    interface EdmundsForumPost { recordType: string; primaryId: number; discussionId: number | null; categoryId: number | null; title: string; summary: string; url: string; dateInserted: string | null; authorName: string | null; authorId: number | null; breadcrumbs: EdmundsBreadcrumb[] }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/edmunds/searchForumPosts

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.edmunds.searchForumPosts({ term: "Honda Accord lease" });
  • searchForumsFull-text search of the Edmunds car forums (discussions and comments) with excerpts and breadcrumbs.

    Arguments

    NameTypeRequired
    querystringYes
    limitnumberNo

    Returns EdmundsForumResult[]

    interface EdmundsBreadcrumb { name: string; url: string }
    
    interface EdmundsForumResult { recordType: string; recordId: number; discussionId: number | null; categoryId: number | null; title: string; excerpt: string; url: string; dateInserted: string | null; breadcrumbs: EdmundsBreadcrumb[] }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/edmunds/searchForums

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.edmunds.searchForums({ query: "Honda Accord lease", limit: 5 });

Use it from code