# Shlok Bam's portfolio (remote · shlokbam.in) Ask about Shlok Bam, AI engineer: projects, experience, skills, patents. Live, read-only. - Trust score: 76/100 (medium) - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-05 ## Components - remote · `shlokbam.in`: 76/100 (this document), [markdown](https://verifymcp.io/servers/shlokbam-portfolio/shlokbam.md), [page](https://verifymcp.io/servers/shlokbam-portfolio/shlokbam) ## Channel facts - Endpoint: `https://shlokbam.in/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.2.1` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-11-05. - **Endpoint Security**: 80/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 81/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 1854 tokens (~185/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 7/100 - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a current MCP spec version (2026-07-28). ## Install ### How do I install the Shlok Bam's portfolio MCP server? Shlok Bam's portfolio is a hosted endpoint at https://shlokbam.in/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http shlokbam-portfolio 'https://shlokbam.in/mcp' ``` ### Cursor ```json { "mcpServers": { "shlokbam-portfolio": { "url": "https://shlokbam.in/mcp" } } } ``` ### VS Code ```json { "servers": { "shlokbam-portfolio": { "type": "http", "url": "https://shlokbam.in/mcp" } } } ``` ### Codex ```toml [mcp_servers.shlokbam-portfolio] url = "https://shlokbam.in/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "shlokbam-portfolio": { "type": "remote", "url": "https://shlokbam.in/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add shlokbam-portfolio --url 'https://shlokbam.in/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: shlokbam-portfolio: url: "https://shlokbam.in/mcp" ``` ### Netclaw ```json { "McpServers": { "shlokbam-portfolio": { "Transport": "http", "Url": "https://shlokbam.in/mcp" } } } ``` ### Vellum ```bash assistant mcp add shlokbam-portfolio -t streamable-http -u 'https://shlokbam.in/mcp' ``` ### Other ```json { "mcpServers": { "shlokbam-portfolio": { "type": "http", "url": "https://shlokbam.in/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-11-05 (score 76, +1) No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-11-04 (score 75, 0) - [functional improvement] Stability: unverified → 0.03 ### 2026-11-03 (score 75) First indexed and scored. ## MCP tools (10) ### `get_profile` (~147 tokens) Profile overview Overview of Shlok Bam: summary, current role, education, location and time zone, what he is open to (roles, relocation), story, headline numbers, what he is focused on this month, contact details (email, phone, contact form) and links (résumé, LinkedIn, GitHub, LeetCode, journal). Takes no input. Call it first for any general question, or for contact details. For his work use list_projects and get_project; for jobs and clubs, get_experience; for anything specific, search_portfolio. Data comes from the live site, refreshed about every 10 minutes. Pay is not included. ### `list_projects` (~351 tokens) List projects List Shlok's projects in order of importance (the first five are flagships). Each entry has name, slug, field, one-line summary, tech stack, live demo and code links, its page on the portfolio, and live GitHub details (stars, language, topics, last update) when the code is in a public repository. Filters combine (all must match); a filter that matches nothing returns count 0, not an error. GitHub details are cached up to 6 hours and are missing for private repositories or when GitHub can't be reached. Use get_project for one project's full write-up and metrics, and search_portfolio for topics that are not projects (a skill used at work, an award). Input parameters: - `category` (string): Only one kind of project: "ai" (AI, ML and agents), "web" (full-stack and web apps), "devops" (CI/CD and infrastructure), "cloud" (serverless and cloud services), or "all". A project can be in more t… - `flagship_only` (boolean): Only the five flagship projects (his most important work). Combines with the other filters. - `include_other_repos` (boolean): Also return otherRepos: his public GitHub repositories the portfolio doesn't feature (forks left out), with GitHub's description, language, stars and last update. - `tech` (string): Only projects using this technology: case-insensitive, matched as part of each tech name and of the write-up, so "lang" finds LangGraph and LangChain. Examples: "LangGraph", "React", "AWS". Empty for… ### `get_project` (~230 tokens) Project details Full details of one of Shlok's projects: what it does and how it is built, results and metrics, highlights, tech stack, rank, live GitHub details, and links (live demo, code, blog post, portfolio page, and the case study for DailyDiff). The name is matched case-insensitively, ignoring punctuation: first exactly against the project name, slug or GitHub repository name, then as part of a name ("workforce" finds the Enterprise Workforce Training Platform). If no featured project matches, his public GitHub repositories are tried and GitHub's details are returned with a note. If nothing matches, the result is {"error", "projects": [every project name]} so you can retry with a valid name. Use list_projects first when you don't know the name. Input parameters: - `name` (string, required): A project name, slug or GitHub repository name, any case; part of a name also works. Examples: "DailyDiff", "PaisaWise", "lms", "enterprise-workforce-training-platform". ### `get_experience` (~99 tokens) Experience, leadership and education Shlok's work experience (internships), leadership roles (student clubs) and education, each list newest first. Every entry has role, organisation, when, type, what he did (points), the organisation's website and links to certificates where they exist. Takes no input. Pay and confidential client details are not included. For patents, awards and certifications use get_achievements; for projects, list_projects. ### `get_achievements` (~170 tokens) Patents, awards and certifications Shlok's recognition and proof of work: patents (three, as co-inventor: title, status, office, reference number, summary and a link to the document), awards and hackathon results (organiser, date, result, certificate links), certifications (issuer, date, certificate link) and community work (mentoring, volunteering, event anchoring). Returns every part, or only the one named in kind, plus a link to the page on the portfolio that shows them. For jobs and club roles use get_experience. Input parameters: - `kind` (string): Which part to return: "patents", "awards" (hackathons and programs), "certifications", "community" (mentoring and volunteering), or "all" for everything. ### `get_skills` (~127 tokens) Skills Shlok's skills in eight groups (Generative AI, LLM evaluation & safety, machine learning, languages, web, databases, cloud & DevOps, core CS), strongest first within each group. Each skill has a level (core, strong, working or exploring) and usedIn: up to six of his projects that list it in their stack or mention it in their write-up (matched by name, so treat it as a pointer, not a complete list). Takes no input. For proof of a skill, open those projects with get_project. ### `get_writing` (~142 tokens) Blog posts Shlok's technical blog posts (his journal), newest first: title, date, topic tag, summary and link. The topic filter is case-insensitive and matches part of a post's topic tag, title or summary ("agent" finds posts tagged Agents); leave it empty for every post. No match returns count 0 and an empty list. For the projects the posts describe, use get_project. Input parameters: - `topic` (string): Only posts about this: case-insensitive, matched as part of the topic tag, title or summary. Examples: "Agents", "RAG", "DevOps", "MCP". Empty for all posts. ### `get_resume` (~72 tokens) Résumé Links to Shlok's résumé: the PDF download and a web version with the same content, plus his title, summary, current role and education. Takes no input. The résumé itself is in those documents; for the same facts as structured data use get_experience, get_skills and list_projects. ### `get_activity` (~125 tokens) Recent GitHub activity What Shlok has been building lately, live from GitHub: commit counts for the last 7 and 30 days, how many repositories he touched this week, and his 12 most recent commits (repository, message, date, link). Only public repositories; scheduled and automated commits (DailyDiff's daily publish, merges) are left out. Cached up to 30 minutes. If GitHub can't be reached it returns {"error", "github"} instead. Takes no input. For what he is focused on this month, see get_profile (rightNow). ### `search_portfolio` (~215 tokens) Search the portfolio Search everything in Shlok's portfolio (projects, experience, leadership, education, patents, awards, certifications, community work and blog posts) for a word or topic. Returns up to 8 matches, best first, each with its type, title, a snippet and a link; no match returns an empty results list. Use it for specific questions the other tools don't answer directly, such as where he used a technology or whether he has done something. For a known project use get_project; for the full list of projects, list_projects; for jobs, get_experience; for patents and awards, get_achievements. Input parameters: - `query` (string, required): One or more words, any case; punctuation is ignored. Each word is matched at the start of words in the text ("eval" finds evaluation), matches in a title count more, and the exact phrase scores extra… ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/shlokbam-portfolio/shlokbam#diagnostics ## Score history - 2026-11-05: 76 - 2026-11-04: 75 - 2026-11-03: 75 ## Common questions ### What is the Shlok Bam's portfolio MCP server? Shlok Bam's portfolio is an MCP server listed in the public MCP registry as io.github.shlokbam/portfolio. Ask about Shlok Bam, AI engineer: projects, experience, skills, patents. Live, read-only. This page covers its hosted endpoint (https://shlokbam.in/mcp). ### Is the Shlok Bam's portfolio MCP server safe to use? Shlok Bam's portfolio scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the Shlok Bam's portfolio MCP server expose? Shlok Bam's portfolio exposes 10 tools: get_profile, list_projects, get_project, get_experience, get_achievements, and 5 more. Their descriptions and schemas cost roughly 1,678 tokens of context every time the server is loaded. ### Does the Shlok Bam's portfolio MCP server require authentication? No. We connected to Shlok Bam's portfolio without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the Shlok Bam's portfolio MCP server still maintained? Shlok Bam's portfolio is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://shlokbam.in/mcp - Repository: https://github.com/shlokbam/Portfolio - Website: https://shlokbam.in/ai - Changelog RSS feed: https://verifymcp.io/servers/shlokbam-portfolio/shlokbam.xml - Changelog JSON feed: https://verifymcp.io/servers/shlokbam-portfolio/shlokbam.json - HTML version of this page: https://verifymcp.io/servers/shlokbam-portfolio/shlokbam