portfolio-mcp
A Model Context Protocol server that enables AI agents to query Saagar Patel's writing, projects, and benchmark results from a static corpus, without scraping HTML.
README
portfolio-mcp
The agent-native layer of saagarpatel.dev: a Model Context Protocol server that lets any AI agent query Saagar's writing, projects, and benchmark results directly, instead of scraping HTML.
Read-only. Stateless. Public. No auth, no tracking, no database, no runtime egress.
How it fits
The website stays a pure static site. This server is a sibling, not a backend bolted onto it:
- Layer 0 (in the
portfolio-indexrepo): the build emits a static machine corpus —corpus-index.json, per-documentcorpus/<id>.json, and.well-known/mcp.json— served alongside the HTML. Already public. - Layer 1 (this repo,
src/index.ts): a stateless Cloudflare Worker that bakes the Layer 0 corpus into its bundle and serves it over MCP (streamable HTTP, theWebStandardStreamableHTTPServerTransport). Zero runtime fetches. - Layer 2 (this repo,
src/stdio.ts): the same server over stdio, for running locally vianpx saagar-portfolio-mcp. Identical tool/resource/prompt surface.
The shared core (src/server.ts) is transport-agnostic; both layers wrap it.
Tool surface
All read-only (readOnlyHint: true). No tool takes a URL or filesystem path (no
SSRF / exfil surface).
| Tool | Purpose |
|---|---|
search |
BM25 over the whole corpus; optional section filter, limit |
get_document |
Full Markdown of one document by id |
list_corpus |
The table of contents; optional type filter |
get_profile |
The "who is this" card (about / now / uses) |
list_projects |
Curated public-safe projects + anonymized aggregates |
get_operant_results |
Public, sanitized OPERANT calibration results (per-model OCS) |
Documents are also exposed as Resources (portfolio://essays/{slug}, book/{slug},
notes/{slug}, portfolio://profile), and there are two Prompts:
introduce_saagar and summarize_writing_on (grounded in a live search).
Retrieval
BM25 over a baked index (no embeddings in v1 — the corpus is ~50 small docs and the calling LLM supplies the semantics). Titles are boosted. Embeddings are a measured Phase 3 upgrade, added only if retrieval quality proves insufficient.
Layout
src/
types.ts corpus + projects + operant shapes
bm25.ts dependency-free BM25 + snippet (pure)
tools.ts createTools(corpus) -> the 6 tools (pure, injectable)
corpus.ts loads the baked corpus + accessors
corpus.generated.ts AUTO-GENERATED by build:corpus
server.ts buildServer(): shared MCP core (tools + resources + prompts)
index.ts Cloudflare Worker transport (streamable HTTP)
stdio.ts Layer 2 stdio transport (the npx CLI)
scripts/
build-corpus.mjs bakes Layer 0 (+ OPERANT) into corpus.generated.ts
probe-mcp.mjs probes an MCP HTTP endpoint: initialize, tools/list, search, OPERANT
smoke-mcp.sh boots wrangler dev, drives the MCP protocol under workerd
audit-mcp.sh connected MCPAudit scan of this server (dogfood)
test/ vitest: bm25, tools, full-protocol server tests
Develop
npm install
npm run build:corpus # bake from ../portfolio-index (or --url=https://saagarpatel.dev)
npm run typecheck
npm test
npm run dev # wrangler dev -> http://localhost:8787/mcp
bash scripts/smoke-mcp.sh # end-to-end MCP smoke under the real workerd runtime
npm run probe:mcp # live Worker probe, or set PORTFOLIO_MCP_ENDPOINT
Inspect either transport with the MCP inspector:
npx @modelcontextprotocol/inspector http://localhost:8787/mcp # Layer 1 (HTTP)
npx @modelcontextprotocol/inspector node dist/stdio.js # Layer 2 (stdio, after build:cli)
Deploy (Layer 1)
npm run build:corpus && npm run deploy # wrangler deploy
npm run probe:mcp # post-deploy live MCP readback
Operator-gated (needs Cloudflare auth). v1 deploys to portfolio-mcp.<account>.workers.dev;
mcp.saagarpatel.dev stays parked until DNS is live and MCP-verified. A one-off
wrangler deploy --domain mcp.saagarpatel.dev can attach a Cloudflare trigger, but the
hostname did not resolve while saagarpatel.dev stayed on third-party/Vercel DNS. Keep
.well-known/mcp.json on the Worker URL until a replacement endpoint passes live checks.
wrangler.jsonc pins workers_dev: true so the public Worker URL stays live during any
future custom-domain experiments; do not remove it unless the website manifest has already
moved to a verified replacement endpoint.
Publish (Layer 2)
npm install -D esbuild # bundling dep (declared in package.json)
npm run build:corpus && npm run build:cli # -> dist/stdio.js
# remove "private": true, then: npm publish
Sign the manifest (optional trust signal)
Ed25519-sign .well-known/mcp.json so an agent or registry can verify it authentically
comes from Saagar. Zero dependencies (Node built-in crypto):
node scripts/sign-manifest.mjs gen-key # one-time; private key -> .signing/ (gitignored, NEVER commit)
node scripts/sign-manifest.mjs sign # writes <manifest>.sig + publishes mcp-ed25519.pub
node scripts/sign-manifest.mjs verify # checks manifest bytes against .sig + public key
Defaults target the sibling portfolio-index manifest (override with --manifest=/--key=/--pub=/--sig=).
Commit the .sig + mcp-ed25519.pub (never the private key) into portfolio-index next to the manifest, then
redeploy the site. Re-run sign whenever the manifest changes (it signs the exact served bytes).
Audit posture
Designed to pass MCPAudit / mcp-trust (Saagar's own tools): only the inbound MCP
transport, no shell_execution / file_access / destructive / exfiltration, and no
caller-controlled egress (the corpus is baked). All tools are annotated read-only with
plain, non-injectable descriptions. bash scripts/audit-mcp.sh runs a connected scan.
Dogfooding this server surfaced a substring-matching false-positive bug in MCPAudit (it
matched port inside portfolio://); that fix lives in the MCPAudit repo and cut this
server's findings 62 → 14. The genuine tool surface scans clean (high_risk_servers: 0).
Status
- Built + verified: Layers 0–2. Shared core + 6 tools + Resources + 2 prompts +
get_operant_results. typecheck clean; 26 tests pass (incl. full MCP protocol via the fetch handler);wrangler devworkerd smoke green; live Worker probe green on 2026-06-27; connected MCPAudit dogfood done. - Gated / next:
mcp.saagarpatel.devcustom domain (DNS decision), publish the stdio package (esbuild install +npm publish), glama.ai registry listing, and an Ed25519-signed.well-known/mcp.json.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。