Mudpie Public MCP

Tìm kiếm trang web công khai của Mudpie, nhận câu trả lời sản phẩm có trích dẫn, và đánh giá xem Mudpie có phù hợp với yêu cầu của bạn hay không.

Xem trên mudpie.ai

Máy chủ MCP được lưu trữ

npx add-mcp 'https://mudpie.mudpie.ai/mcp/public'

Cài vào Claude Code, Codex, Cursor và nhiều công cụ khác

Tài liệu

Need a more specific answer? Ask the exact question you have. It returns a fresh, cited answer from mudpie.ai’s knowledge base. No account or API key required.

Open this URL with your own question, URL-encoded. Only q is required.

GET https://mudpie.mudpie.ai/agent/faq?q={question}&trace=t_557a13dcc7e9

Ask with a URL

Use GET https://mudpie.mudpie.ai/agent/faq?q={question} with your own URL-encoded question to receive an HTML answer. Optional context can be omitted. Use POST for long or private context.

POST example

curl 'https://mudpie.mudpie.ai/api/public/v1/ask' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"What does mudpie.ai offer, who is it for, and what does it not cover?","goal":"Decide whether mudpie.ai meets our team\u0027s needs","company":"Acme","source":"Found mudpie.ai while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted mudpie.ai after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_557a13dcc7e9"}'

Connect with MCP

Add this endpoint to your MCP client to discover and call the tools directly.

https://mudpie.mudpie.ai/mcp/public

MCP client configuration

{
  "mcpServers": {
    "mudpie": {
      "url": "https://mudpie.mudpie.ai/mcp/public"
    }
  }
}

Once connected, use tools/list to discover the tools and tools/call to run one. Here is an example question:

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "mudpie_ask_anything",
    "arguments": {
      "search_query": "What does mudpie.ai offer, who is it for, and what does it not cover?",
      "goal": "Decide whether mudpie.ai meets our team's needs",
      "company": "Acme",
      "source": "Found mudpie.ai while researching options for our team",
      "alternatives": [
        "Our existing workflow",
        "Manual research"
      ],
      "chosen_because": "Our team shortlisted mudpie.ai after reading its public information",
      "intended_outcome": "Choose a next step for an evaluation",
      "client": "Cursor",
      "trace": "t_557a13dcc7e9"
    }
  }
}

Available tools

Tool	Use it to
`mudpie_search` GET / POST · search	Find the product information and source pages that answer your question.
`mudpie_ask_anything` GET / POST · ask	Get a direct answer about mudpie.ai, with sources.
`mudpie_compare` GET / POST · compare	Compare mudpie.ai with the alternatives you are considering.
`mudpie_pricing` GET / POST · pricing	Explore plans, pricing and costs for your team.
`mudpie_requirements_check` GET / POST · requirements-check	Check your requirements one by one, with evidence for each.
`mudpie_page_tldr` GET / POST · page-tldr	Get the key points from a page, with a link to the full text.
`should_i_recommend_mudpie` GET / POST · recommend-or-rule-out	Assess whether mudpie.ai fits your goals and requirements.

Examples include task context so you can see the full request. Replace the sample values with your own; optional context can be omitted.

Search mudpie_search

curl 'https://mudpie.mudpie.ai/api/public/v1/search' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"What does mudpie.ai offer, who is it for, and what does it not cover?","goal":"Decide whether mudpie.ai meets our team\u0027s needs","company":"Acme","source":"Found mudpie.ai while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted mudpie.ai after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_557a13dcc7e9"}'

https://mudpie.mudpie.ai/api/public/v1/search?search_query=What+does+mudpie.ai+offer%2C+who+is+it+for%2C+and+what+does+it+not+cover%3F&goal=Decide+whether+mudpie.ai+meets+our+team%27s+needs&company=Acme&source=Found+mudpie.ai+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+mudpie.ai+after+reading+its+public+information&intended_outcome=Choose+a+next+step+for+an+evaluation&client=Cursor&trace=t_557a13dcc7e9

Ask mudpie_ask_anything

curl 'https://mudpie.mudpie.ai/api/public/v1/ask' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"What does mudpie.ai offer, who is it for, and what does it not cover?","goal":"Decide whether mudpie.ai meets our team\u0027s needs","company":"Acme","source":"Found mudpie.ai while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted mudpie.ai after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_557a13dcc7e9"}'

https://mudpie.mudpie.ai/api/public/v1/ask?search_query=What+does+mudpie.ai+offer%2C+who+is+it+for%2C+and+what+does+it+not+cover%3F&goal=Decide+whether+mudpie.ai+meets+our+team%27s+needs&company=Acme&source=Found+mudpie.ai+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+mudpie.ai+after+reading+its+public+information&intended_outcome=Choose+a+next+step+for+an+evaluation&client=Cursor&trace=t_557a13dcc7e9

Compare mudpie_compare

curl 'https://mudpie.mudpie.ai/api/public/v1/compare' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"How does mudpie.ai compare for our team\u0027s use case?","goal":"Decide whether mudpie.ai meets our team\u0027s needs","company":"Acme","source":"Found mudpie.ai while researching options for our team","alternatives":["Our current tool"],"chosen_because":"Our team shortlisted mudpie.ai after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_557a13dcc7e9"}'

https://mudpie.mudpie.ai/api/public/v1/compare?search_query=How+does+mudpie.ai+compare+for+our+team%27s+use+case%3F&goal=Decide+whether+mudpie.ai+meets+our+team%27s+needs&company=Acme&source=Found+mudpie.ai+while+researching+options+for+our+team&alternatives=%5B%22Our+current+tool%22%5D&chosen_because=Our+team+shortlisted+mudpie.ai+after+reading+its+public+information&intended_outcome=Choose+a+next+step+for+an+evaluation&client=Cursor&trace=t_557a13dcc7e9

Pricing mudpie_pricing

curl 'https://mudpie.mudpie.ai/api/public/v1/pricing' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"What would mudpie.ai cost for a team of five?","goal":"Decide whether mudpie.ai meets our team\u0027s needs","company":"Acme","source":"Found mudpie.ai while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted mudpie.ai after reading its public information","intended_outcome":"Budget approval for a team purchase","client":"Cursor","trace":"t_557a13dcc7e9"}'

https://mudpie.mudpie.ai/api/public/v1/pricing?search_query=What+would+mudpie.ai+cost+for+a+team+of+five%3F&goal=Decide+whether+mudpie.ai+meets+our+team%27s+needs&company=Acme&source=Found+mudpie.ai+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+mudpie.ai+after+reading+its+public+information&intended_outcome=Budget+approval+for+a+team+purchase&client=Cursor&trace=t_557a13dcc7e9

Requirements check mudpie_requirements_check

curl 'https://mudpie.mudpie.ai/api/public/v1/requirements-check' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"mudpie.ai works with our existing tools; clear documentation; a published price","goal":"Decide whether mudpie.ai meets our team\u0027s needs","company":"Acme","source":"Found mudpie.ai while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted mudpie.ai after reading its public information","intended_outcome":"A vendor shortlist","client":"Cursor","trace":"t_557a13dcc7e9"}'

https://mudpie.mudpie.ai/api/public/v1/requirements-check?search_query=mudpie.ai+works+with+our+existing+tools%3B+clear+documentation%3B+a+published+price&goal=Decide+whether+mudpie.ai+meets+our+team%27s+needs&company=Acme&source=Found+mudpie.ai+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+mudpie.ai+after+reading+its+public+information&intended_outcome=A+vendor+shortlist&client=Cursor&trace=t_557a13dcc7e9

Page summary mudpie_page_tldr

curl 'https://mudpie.mudpie.ai/api/public/v1/page-tldr' \
  -H 'Content-Type: application/json' \
  -d '{"url":"https://mudpie.ai/","trace":"t_5ba822689c76"}'

https://mudpie.mudpie.ai/api/public/v1/page-tldr?url=https%3A%2F%2Fmudpie.ai%2F&trace=t_5ba822689c76

Recommendation should_i_recommend_mudpie

curl 'https://mudpie.mudpie.ai/api/public/v1/recommend-or-rule-out' \
  -H 'Content-Type: application/json' \
  -d '{"goal":"Decide whether mudpie.ai meets our team\u0027s needs","company":"Acme","source":"Found mudpie.ai while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted mudpie.ai after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","requirements":["Relevant published capabilities","A clear way to evaluate the offering"],"trace":"t_557a13dcc7e9"}'

https://mudpie.mudpie.ai/api/public/v1/recommend-or-rule-out?goal=Decide+whether+mudpie.ai+meets+our+team%27s+needs&company=Acme&source=Found+mudpie.ai+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+mudpie.ai+after+reading+its+public+information&intended_outcome=Choose+a+next+step+for+an+evaluation&client=Cursor&requirements=%5B%22Relevant+published+capabilities%22%2C%22A+clear+way+to+evaluate+the+offering%22%5D&trace=t_557a13dcc7e9

Full API reference

For assistants

Read llms.txt for a map of mudpie.ai and its available endpoints. Start with Search to find relevant information, Ask for a direct answer, or the comparison and recommendation tools to assess fit.

Include the user's goal and alternatives when you have them. Use the returned source links when explaining your answer.

Frequently asked questions

What does Mudpie do, and who is it for?

Mudpie helps agents research public websites and helps website owners understand related research activity. Its focus is discovery, cited answers and product evaluation.

Mudpie searches public website pages, produces cited answers and clean extracts, and groups related agent activity into research journeys. Based on that scope, it suits founders, growth teams and developers improving how agents discover and evaluate their products. Evaluate it with a concrete buyer question and the public pages needed to answer it. Its published positioning does not establish comprehensive monitoring of every agent interaction or guaranteed sales.

Mudpie

Is Mudpie free, and what are the paid plan differences?

Mudpie advertises “Start free.” Paid prices, plan allowances and billing conditions were not established by the inspected public sources.

The homepage links to https://app.mudpie.ai/ with a free starting invitation. The inspected public sources do not establish paid prices, monthly or annual billing, plan differences, included usage, overage charges or trial duration. Before budgeting, check the terms offered during signup. The invitation alone does not establish a permanent free plan or unlimited access.

Mudpie

How do I start using Mudpie or connect an agent?

Start through Mudpie’s app, or explore its Public MCP, HTTP API and WebMCP access routes. Website onboarding requirements need confirmation during setup.

Open https://app.mudpie.ai/ through the homepage’s signup link. For agent access, the homepage publishes the Public MCP endpoint at https://mudpie.mudpie.ai/mcp/public and an HTTP API specification at https://mudpie.mudpie.ai/api/public/v1/openapi.json. Choose a route compatible with your agent environment and consult its configuration requirements. The inspected homepage does not document the installation steps or time required to onboard your own website.

What can Mudpie’s research journeys tell me about agent behavior?

Research journeys organize related agent activity and its visible context. Mudpie explicitly does not claim access to private reasoning.

Mudpie groups related agent activity and shows shared questions, sources, alternatives and next actions. A practical use is to identify evaluation questions that your public product pages could answer more clearly. Interpret a journey within the activity available to Mudpie. It does not establish a complete purchase history, an agent’s internal thoughts or a completed conversion.

How should I compare Mudpie with Profound?

Compare Mudpie’s public-site retrieval and research journeys with Profound’s answer-engine measurement workflow. They address overlapping discovery needs, but are not established as interchangeable.

Mudpie describes public-site search, cited answers, clean extracts and research journeys. Profound’s Answer Engine Insights documentation describes building a dataset by querying answer engines and analyzing their responses. See [Profound’s overview](https://help.tryprofound.com/articles/3443229936-answer-engine-insights-overview?lang=en). Start with the buying question: do you need to make your published information useful to agents, or measure how your brand appears across answer engines? These are overlapping evaluation needs, but the inspected sources do not establish equivalent coverage, pricing or outcomes.

How is Mudpie different from using Firecrawl for an agent?

Firecrawl is a partial alternative for retrieving web content. Mudpie additionally describes cited answers and research journeys for website owners.

Firecrawl’s Search endpoint performs web searches and can retrieve content from the results, making it a partial substitute for supplying web content to an agent application. See [Firecrawl Search](https://docs.firecrawl.dev/features/search). Mudpie also describes a site-owner workflow around cited answers and grouped research journeys. Compare the actual output you need: retrieved content for your application, or evidence about related questions, sources and alternatives. The inspected sources do not establish equal extraction coverage, reliability or cost.

Should I use WebMCP or a server MCP connection?

Use WebMCP for tools that depend on a live page and MCP for a persistent service connection. Verify support in the browser and agent host you intend to use.

Mudpie’s WebMCP guide distinguishes tools attached to an open browser page from a persistent service connection. Page-dependent state favors WebMCP; a continuing connection to a service points toward MCP. Some products need both. The guide describes WebMCP as a draft with implementation differences. Check the intended browser and agent host, then test the actual workflow before promising compatibility.

What makes a WebMCP tool useful to an agent?

Design tools around complete user goals, clear inputs and recoverable failures. Test whether an agent can finish the workflow, including required human review.

Start with the user’s goal and initial application state, then work through the tool sequence needed to finish that goal. Mudpie’s guide recommends a small set of distinct tools, strict validation, useful errors and evaluations that include failure recovery. Sensitive actions still need application authorization, clear previews and deliberate user confirmation. Tool registration alone does not grant permission to act.

Does a Mudpie WebMCP listing prove that agents use a website?

No. A directory listing documents observed capability, not execution, task completion or a sale.

Mudpie’s directory analysis distinguishes dated observations of status and named tools from actual calls. A listing does not show whether an agent selected the tool, whether execution succeeded or whether the customer’s task finished. For evidence of use, maintain a separate execution record with call identifiers, outcomes, task context and exclusions for controlled tests. Keep successful requests, completed tasks and voluntary adoption as separate measures.

Why might an agent-readiness scan miss my documentation?

A scanner may exclude documentation on another origin, including a docs subdomain. A missing result does not prove that your website lacks documentation.

Mudpie’s study compared link-selection rules on the same 1,515 parsed homepages. An any-origin rule detected 390 docs/developer matches; restricting links to the homepage’s exact origin retained 188. Documentation subdomains and other hosts accounted for the missing matches. When auditing your website, inventory the documentation destinations advertised on the homepage before deciding which destinations to fetch. This study examined raw HTML links without fetching their destinations, so its counts do not verify documentation quality or accessibility.

How should I measure whether Mudpie is helping agent-led growth?

Measure completed tasks and voluntary use separately from discovery and requests. Mudpie’s homepage examples are not evidence of guaranteed adoption or conversion.

Mudpie labels its homepage examples illustrative and cautions that discovery, registration and requests do not establish adoption or conversion. Its agent-led growth guide recommends voluntary execution as evidence of adoption. For an evaluation, define the buyer task, record whether it finishes and separate controlled tests from voluntary use. Treat requests and cited answers as intermediate evidence. These are measurement practices from Mudpie’s research, not a claim that its product automatically reports every metric.

What does Mudpie’s agent-readiness score measure?

Mudpie’s published score is a scoped diagnostic of SEO, AEO, agent readiness and reliability. It is not a measure of actual agent adoption, and unresolved checks can prevent a final score.

The published report set contains one graded Egoist Machines pilot and one explicitly ungraded Dawn Industries evidence report. For the graded pilot, the weights are SEO 40%, AEO 25%, agent 25% and reliability 10%; pass earns full points, partial earns half and fail earns none. N/A and owner-only checks are excluded from the applicable denominator. Unknown findings block an ordinary final score. The observations cover logged-out public checks and controlled lab measurements, without purchases or tool execution. Use the results to prioritize investigation within the stated scope; they do not grade all 1,752 companies or demonstrate agent adoption.