Live MCP Server

Returns a one-paragraph professional summary of Asish Madala — current role, years of experience, defining strengths, headline metrics, and links to LinkedIn / GitHub. Use this as the first call when you have no prior context about Asish. Faster and cheaper than `ask` for general 'who is this person' questions.

Returns 1-3 canonical interview stories from Asish's career, each with title, role, period, summary, key actions, results, and metrics. Filter by `topic` to find stories relevant to a specific theme. Use this when a recruiter asks 'tell me about a time when...' or wants to drill into a particular kind of work (agentic AI, RAG, MCP, evaluations, shipping velocity, leadership).

Analyzes a job description and returns a fit verdict for Asish Madala. Returns: fitScore 0-100, scoreReasoning, three matching career stories with metrics and JD alignment, two honest gaps with interview mitigation strategies, and a tailored 4-sentence cover paragraph. Takes 6-10 seconds. Use this when a recruiter pastes a JD or asks 'would he be a fit for X?'. This is the same engine that powers https://asish.xyz/fit — calling it via MCP returns the same shape, one-shot (not streamed).

General purpose Q and A about Asish Madala, grounded in his portfolio content. Returns a 2 to 4 paragraph answer plus a list of source citations (heading and snippet). Use this as the catch all when other tools do not fit (for example 'how does he think about prioritization?' or 'what is his leadership style?'). Behavioral interview questions, the kind that start with tell me about a time, get a special answer: one true story from a matched case study, told with real numbers, on a larger model. Answers are written in Asish's voice, in the first person.

Lists every live app in the asish.xyz playground with its URL, status, what it does, and which tools on this MCP server run the same engine. Covers PM Studio and its four generators, the JD to Fit analyzer, the vibe code prototype builder, the lead qualification agent, the eval harness, and this MCP server itself. Call this first for a map of everything you can run from here.

Turns a short feature description into a complete one page PRD: problem statement, goals, items out of scope, prioritized user stories, functional and quality requirements, measurable success metrics, and risks with mitigations. Same engine as the PRD Generator at https://asish.xyz/pm-studio. Takes roughly 15 to 40 seconds. Returns structured JSON plus ready to paste markdown.

Scores 2 to 8 feature ideas with the RICE framework: reach, impact, confidence, and effort, each with a written rationale, plus computed RICE scores and a ranked order. Same engine as the RICE Prioritizer at https://asish.xyz/pm-studio. Takes roughly 10 to 30 seconds. Returns the ranked table as JSON and markdown.

Turns rough working notes into a polished stakeholder update as an email, a Slack post, or an executive summary, in the tone you choose. Uses only facts present in the notes and never invents numbers. Same engine as the Update Composer at https://asish.xyz/pm-studio. Takes roughly 5 to 20 seconds and returns markdown.

Expands a feature description into an epic with 3 to 6 user stories, each with a priority, Given When Then acceptance criteria, and edge cases an engineering team can pick up without a meeting. Same engine as the Story Generator at https://asish.xyz/pm-studio. Takes roughly 10 to 30 seconds. Returns structured JSON plus markdown.

Builds a working demo from a plain English feature idea in two steps: first a compact PRD, then one self contained React component in TypeScript with Tailwind styling and hardcoded mock data, safe for sandboxed rendering. Same engine as https://asish.xyz/prototype. This is the slowest tool here: expect 20 to 45 seconds. Returns the PRD and the component source, or a reason if the generated code failed the safety scan.

Runs the four step lead qualification agent for a company name or LinkedIn company URL: resolves the company, gathers live web signals through Tavily search, scores fit against an ideal customer profile across stage, domain, hiring, and geography, then drafts a personalized outreach email. Same agent as https://asish.xyz/lead. Expect 15 to 35 seconds. Pass your own ICP text or use the default.

Runs the LLM evaluation demo: support ticket triage cases against two prompt versions, scored by exact label extraction with an LLM judge fallback, returning per case results and pass rates for both prompts. Defaults to the five canonical cases and prompts from the site; you may supply your own, up to 8 cases. Same harness as https://asish.xyz/evals. Expect 15 to 40 seconds.

Returns Asish's shippable projects (not career stories — those are in `get_top_stories`). Each project has title, tags, year, description, stack, links, and outcome metrics. Optional `tag` filter for substring search. Use this when the user asks 'what has he built' or wants concrete deliverables for a tech stack.

Returns Asish's work history as a structured array of roles, most-recent first. Each role has company, title, dates, location, a 1-2 sentence summary, and 3-5 highlight bullets with metrics. Optional filters: `company` (substring match) and `since` (ISO date). Use this when the user asks about a specific company, timeline, or 'show me his recent work'.

Returns Asish's formal education — Carnegie Mellon University (M.S. Computational Engineering) and Indian Institute of Technology Madras (B.Tech). Each entry has school, degree, dates, focus areas. Use when a recruiter asks about academic background or alma mater.

Returns Asish's awards, recognitions, and notable affiliations. Sparse intentionally — only items a recruiter would find credible and recent. Use when asked about academic / industry recognitions.

Returns Asish's public contact information — email, LinkedIn, GitHub, location, portfolio URL. Use when the user wants to know how to reach Asish or where to find more.