Mudpie Public MCP

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

Need a more specific answer? Ask the exact question you have. It returns a fresh, cited answer from Mudpie’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_1997061ce173

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 offer, who is it for, and what does it not cover?","goal":"Decide whether Mudpie meets our team\u0027s needs","company":"Acme","source":"Found Mudpie while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted Mudpie after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_1997061ce173"}'

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 offer, who is it for, and what does it not cover?",
      "goal": "Decide whether Mudpie meets our team's needs",
      "company": "Acme",
      "source": "Found Mudpie while researching options for our team",
      "alternatives": [
        "Our existing workflow",
        "Manual research"
      ],
      "chosen_because": "Our team shortlisted Mudpie after reading its public information",
      "intended_outcome": "Choose a next step for an evaluation",
      "client": "Cursor",
      "trace": "t_1997061ce173"
    }
  }
}

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, with sources.
mudpie_compare GET / POST · compare	Compare Mudpie 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 fits your goals and requirements.
mudpie_sign_up POST · convert	Email the user a Mudpie sign-in link to start a free account. Submit only an email address the user authorized. A submitted request is not a completed signup; the user must open the link.

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 offer, who is it for, and what does it not cover?","goal":"Decide whether Mudpie meets our team\u0027s needs","company":"Acme","source":"Found Mudpie while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted Mudpie after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_1997061ce173"}'

https://mudpie.mudpie.ai/api/public/v1/search?search_query=What+does+Mudpie+offer%2C+who+is+it+for%2C+and+what+does+it+not+cover%3F&goal=Decide+whether+Mudpie+meets+our+team%27s+needs&company=Acme&source=Found+Mudpie+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+Mudpie+after+reading+its+public+information&intended_outcome=Choose+a+next+step+for+an+evaluation&client=Cursor&trace=t_1997061ce173

Ask mudpie_ask_anything

curl 'https://mudpie.mudpie.ai/api/public/v1/ask' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"What does Mudpie offer, who is it for, and what does it not cover?","goal":"Decide whether Mudpie meets our team\u0027s needs","company":"Acme","source":"Found Mudpie while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted Mudpie after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_1997061ce173"}'

https://mudpie.mudpie.ai/api/public/v1/ask?search_query=What+does+Mudpie+offer%2C+who+is+it+for%2C+and+what+does+it+not+cover%3F&goal=Decide+whether+Mudpie+meets+our+team%27s+needs&company=Acme&source=Found+Mudpie+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+Mudpie+after+reading+its+public+information&intended_outcome=Choose+a+next+step+for+an+evaluation&client=Cursor&trace=t_1997061ce173

Compare mudpie_compare

curl 'https://mudpie.mudpie.ai/api/public/v1/compare' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"How does Mudpie compare for our team\u0027s use case?","goal":"Decide whether Mudpie meets our team\u0027s needs","company":"Acme","source":"Found Mudpie while researching options for our team","alternatives":["Our current tool"],"chosen_because":"Our team shortlisted Mudpie after reading its public information","intended_outcome":"Choose a next step for an evaluation","client":"Cursor","trace":"t_1997061ce173"}'

https://mudpie.mudpie.ai/api/public/v1/compare?search_query=How+does+Mudpie+compare+for+our+team%27s+use+case%3F&goal=Decide+whether+Mudpie+meets+our+team%27s+needs&company=Acme&source=Found+Mudpie+while+researching+options+for+our+team&alternatives=%5B%22Our+current+tool%22%5D&chosen_because=Our+team+shortlisted+Mudpie+after+reading+its+public+information&intended_outcome=Choose+a+next+step+for+an+evaluation&client=Cursor&trace=t_1997061ce173

Pricing mudpie_pricing

curl 'https://mudpie.mudpie.ai/api/public/v1/pricing' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"What would Mudpie cost for a team of five?","goal":"Decide whether Mudpie meets our team\u0027s needs","company":"Acme","source":"Found Mudpie while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted Mudpie after reading its public information","intended_outcome":"Budget approval for a team purchase","client":"Cursor","trace":"t_1997061ce173"}'

https://mudpie.mudpie.ai/api/public/v1/pricing?search_query=What+would+Mudpie+cost+for+a+team+of+five%3F&goal=Decide+whether+Mudpie+meets+our+team%27s+needs&company=Acme&source=Found+Mudpie+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+Mudpie+after+reading+its+public+information&intended_outcome=Budget+approval+for+a+team+purchase&client=Cursor&trace=t_1997061ce173

Requirements check mudpie_requirements_check

curl 'https://mudpie.mudpie.ai/api/public/v1/requirements-check' \
  -H 'Content-Type: application/json' \
  -d '{"search_query":"Mudpie works with our existing tools; clear documentation; a published price","goal":"Decide whether Mudpie meets our team\u0027s needs","company":"Acme","source":"Found Mudpie while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted Mudpie after reading its public information","intended_outcome":"A vendor shortlist","client":"Cursor","trace":"t_1997061ce173"}'

https://mudpie.mudpie.ai/api/public/v1/requirements-check?search_query=Mudpie+works+with+our+existing+tools%3B+clear+documentation%3B+a+published+price&goal=Decide+whether+Mudpie+meets+our+team%27s+needs&company=Acme&source=Found+Mudpie+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+Mudpie+after+reading+its+public+information&intended_outcome=A+vendor+shortlist&client=Cursor&trace=t_1997061ce173

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 meets our team\u0027s needs","company":"Acme","source":"Found Mudpie while researching options for our team","alternatives":["Our existing workflow","Manual research"],"chosen_because":"Our team shortlisted Mudpie 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_1997061ce173"}'

https://mudpie.mudpie.ai/api/public/v1/recommend-or-rule-out?goal=Decide+whether+Mudpie+meets+our+team%27s+needs&company=Acme&source=Found+Mudpie+while+researching+options+for+our+team&alternatives=%5B%22Our+existing+workflow%22%2C%22Manual+research%22%5D&chosen_because=Our+team+shortlisted+Mudpie+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_1997061ce173

Visitor action mudpie_sign_up

Check the inbox and follow the Mudpie sign-in link to finish. The request being submitted does not mean the account was accessed. Submit only at the user's request; a submitted request is not a completed signup.

POST https://mudpie.mudpie.ai/api/public/v1/convert

Read the input schema in the API reference or MCP tools/list.

Open the public next step

Full API reference

For assistants

Read llms.txt for a map of Mudpie 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 which teams should evaluate it?

Mudpie helps agents research products using public website content and helps teams understand related research activity. Evaluate it when agent discovery and product evaluation matter to your growth strategy.

Read more

Mudpie searches published website pages, returns sources, and produces cited answers and clean extracts for agents. It also groups related agent activity into research journeys so teams can examine shared questions, alternatives and potential next actions. Based on that scope, Mudpie is most relevant to founders, growth teams and product teams improving how agents discover and evaluate their products. Its homepage does not establish that it replaces a CRM, product analytics platform or general-purpose agent runtime.

• Mudpie
• Mudpie

Is Mudpie free, and what do paid plans cost?

Mudpie advertises a free starting point. The inspected public sources do not specify paid prices, billing periods or free usage limits.

Read more

The homepage links to app.mudpie.ai with a Start free invitation. The inspected public inventory did not provide a Mudpie pricing page, paid plan comparison, billing period, usage allowance or overage policy. Use the free entry point to investigate the product, but confirm included sites, request limits, seats and paid billing terms before budgeting. The published invitation alone does not establish an unlimited free plan or a particular trial duration.

• Mudpie

How should I start evaluating Mudpie for my website?

Start through Mudpie’s app, then test questions with known answers on your public website. Judge the evaluation by source accuracy and preserved conditions, not just fluent answers.

Read more

Begin with the Start free link on Mudpie’s homepage. The same page links to its MCP and API documentation, Public MCP endpoint, HTTP API specification and example configurations. For a practical evaluation, choose a few questions your public pages already answer, such as product fit, prerequisites and limitations. Check whether the returned answer cites the right page and preserves its conditions; this is an evaluation recommendation, not a documented onboarding requirement or setup-time promise.

• Mudpie
• Mudpie

Should I connect to Mudpie through MCP, the HTTP API or WebMCP?

Mudpie publishes three connection options: Public MCP, HTTP API and WebMCP. Match the option to your agent’s environment, especially whether it works inside a live browser page.

Read more

Mudpie lists Public MCP, an HTTP API and WebMCP as connection options. Its homepage supplies the Public MCP endpoint at https://mudpie.mudpie.ai/mcp/public and links to the HTTP API specification. Mudpie’s WebMCP reading guide distinguishes live-page tools from persistent service connections. Choose the connection around where the agent operates, and verify compatibility with your intended host; the guide explicitly warns that implementations differ.

• Mudpie
• WebMCP 101

What can Mudpie research journeys reveal about an agent’s product evaluation?

Research journeys organize observable questions, sources, alternatives and next actions. Mudpie does not claim access to an agent’s private reasoning.

Read more

Mudpie describes research journeys as groups of related agent activity. The homepage says these can show shared questions, sources, alternatives and next actions, while explicitly withholding any claim to private reasoning. Use those observations to identify missing product explanations or unclear comparisons. Treat an observed question or alternative as evidence of research activity, not proof of a buyer’s internal intent or a completed purchase.

• Mudpie

What should I check if an agent-readiness scan says my documentation is missing?

Check whether the scanner excludes documentation hosted on another origin, including a docs subdomain. A missing result can reflect the collection rule rather than missing documentation.

Read more

Mudpie’s link-scanning research found that an exact-origin restriction excluded documentation links on subdomains and other hosts. Across the same 1,515 parsed homepages, the broader rule identified docs/developer links on 390 companies, compared with 188 under the same-origin rule. For an audit, inventory advertised documentation destinations before choosing what to fetch. Record link discovery separately from successfully reading the destination: the study inspected homepage links and did not verify the linked documentation. These findings are guidance about collector design, not a claim about Mudpie’s current ingestion coverage.

• Same-origin scanning missed docs links on 202 YC homepages
• Same-origin scanning missed docs links on 202 YC homepages

Will using Mudpie guarantee citations in AI answers?

The inspected sources provide no citation guarantee. Mudpie’s published guidance treats AEO changes as experiments whose results depend on the engine, prompt and date.

Read more

Mudpie’s AEO guide recommends retaining SEO fundamentals and treating results as specific to an engine, prompt and date. It presents content structure and prompt research as inputs to experiments, without promising citation improvements. Choose a defined set of buyer questions, record the engine and observation date, and compare repeated results after a specific page change. Keep citation presence separate from clicks and conversions. This follows the publication’s measurement guidance; it is not a claim that Mudpie automatically runs this experiment.

• AEO 101
• AEO 101

How should I interpret Mudpie’s agent-readiness scores?

Treat a readiness score as a diagnostic under a declared ruleset, not proof of agent adoption. The public methods distinguish one graded pilot from an ungraded evidence report.

Read more

Mudpie’s methods page describes one graded Egoist Machines pilot and one explicitly ungraded Dawn Industries evidence report. It does not claim that all 1,752 companies in the separate census received grades. For the graded pilot, the dimension weights are SEO 40%, AEO 25%, agent 25% and reliability 10%. Passing earns full points, partial results earn half, and failed checks earn none; N/A and owner-only checks are excluded from the applicable denominator. Unknown results block an ordinary final score, so compare reports only after checking their rules and evidence boundaries.

• Agent readiness scorecard methods
• Agent readiness scorecard methods

Do Mudpie’s public readiness reports test purchases or successful agent tasks?

No. The published methodology covers public observations and explicitly excludes purchases, form submissions and tool execution.

Read more

Mudpie’s public methodology separates logged-out reads, rendered checks and public machine documents from registration, execution, completion and adoption. It explicitly reports that no login, form submission, purchase or tool execution was performed. Use these reports to assess the documented public surface and identify what still needs testing. If your buying decision depends on an agent finishing a workflow, a readiness report alone does not supply that evidence.

• Agent readiness scorecard methods

What makes a WebMCP tool useful beyond simply registering it?

Design tools around complete user goals, validate inputs and test failure recovery. Registration alone does not demonstrate that an agent can finish the task.

Read more

Mudpie’s WebMCP guide recommends starting with a user’s end goal and initial state, then testing likely tool sequences and recovery from failures. It advises a small set of distinct tools with validation and useful errors rather than reproducing every interface control. Before publishing a workflow, check whether an agent can select the right tool, supply valid inputs and recover when something fails. Verify support in the intended browser and agent host, because the guide distinguishes the proposed standard from individual implementations.