npx -y webvector-cli search "what changed in the MCP spec in 2026?"

# Web research: what changed in the MCP spec in 2026?

**[1]** Streamable HTTP — Model Context Protocol — <https://modelcontextprotocol.io/specification/2026-07-28/…> (score 1.00)
> ### Earlier Streamable HTTP Revisions
> Protocol versions 2025-03-26 through 2025-11-25 also used the Streamable HTTP transport, but in a
> different shape: servers could assign a session via the Mcp-Session-Id header … None of these
> mechanisms are part of this revision.
…
## Sources
- Streamable HTTP — Model Context Protocol — <https://…> [1]

npx -y webvector-cli search "how does reciprocal rank fusion work" --stats

npx -y webvector-cli doctor

claude mcp add webvector -- npx -y webvector-mcp

{
  "mcpServers": {
    "webvector": {
      "command": "npx",
      "args": ["-y", "webvector-mcp"],
      "env": { "BRAVE_API_KEY": "optional — see §7" }
    }
  }
}

"args": ["-y", "-p", "@huggingface/transformers", "-p", "webvector-mcp", "webvector-mcp"]

npm i webvector

import { WebVector } from 'webvector';

const wv = new WebVector();                                        // zero-config
const res = await wv.research('what is reciprocal rank fusion');

console.log(res.markdown);                                         // ready to drop into a prompt
for (const p of res.passages) console.log(p.score, p.citation);    // "[1] Title — https://…"
await wv.close();

const wv = new WebVector({
  search: { provider: 'brave' },                                   // reads BRAVE_API_KEY
  embeddings: { provider: 'openai', model: 'text-embedding-3-small' },
  retrieval: { topK: 8, rerank: 'cohere' },
  store: { mode: 'session' },                                      // reuse pages across calls
});

const res = await wv.research('How does Node 24 handle AbortSignal.any?', {
  relatedQueries: ['AbortSignal.any example'],  // extra angles (also searched)
  freshness: 'year',                            // day | week | month | year
  domainsAllow: ['nodejs.org', 'developer.mozilla.org'],
  sessionId: 'conversation-42',                 // pages already read this session are reused
  onProgress: (p) => console.error(p.stage, p.message),
});

// Vercel AI SDK
import { generateText, isStepCount } from 'ai';
import { webVectorTools } from 'webvector/ai-sdk';
await generateText({ model, tools: await webVectorTools(wv), stopWhen: isStepCount(5), prompt });

// Anthropic Messages API           // OpenAI Responses API            // LangChain.js
import { anthropicTools, runAnthropicTool } from 'webvector/anthropic';
import { openaiTools, runOpenAITool } from 'webvector/openai';
import { langchainTools } from 'webvector/langchain';

// Anything else: plain JSON Schema
import { webResearchToolDefinition } from 'webvector';

npm i -g webvector-cli          # or keep using npx -y webvector-cli …

webvector search "query" [-k 8] [-p 12] [--provider brave] [--embeddings openai] [--rerank local] [--json|--md] [--stats]
webvector fetch <url> [--query "…"]     # one page as Markdown, or just the passages relevant to --query
webvector serp "query"                  # search results only
webvector doctor [--live]               # config, dependencies, provider connectivity, active tier
webvector init                          # writes webvector.config.yaml + .env.example
webvector config                        # print resolved config (secrets redacted)
webvector providers                     # every provider and the env var it reads
webvector mcp [--http]                  # run the MCP server

search:
  provider: duckduckgo          # duckduckgo | brave | serper | serpapi | google-cse | searxng | tavily | tavily-keyless | exa | perplexity | wikipedia
  fallbackProviders: [tavily-keyless, wikipedia]
  resultsPerQuery: 10
embeddings:
  provider: auto                # auto | none | local | openai | openai-compatible | gemini | voyage | cohere | mistral | jina | ollama
  model: Xenova/all-MiniLM-L6-v2   # local aliases: minilm (fast) | granite (quality) | embeddinggemma (best) | bge-small | nomic …
store:
  provider: memory              # memory | chroma | qdrant | pgvector
  mode: ephemeral               # ephemeral (per call) | session (reuse by sessionId, TTL) | persistent (external store)
retrieval:
  topK: 12
  hybrid: true                  # BM25 + vectors fused with RRF (semantic tier)
  queryExpansion: true          # heuristic (no LLM); pass retrieval.llm in code for LLM multi-query
  maxPerSource: 3
  mmr: true
  rerank: false                 # local | cohere | voyage | jina | llm
ingestion:
  maxPages: 10
  maxConcurrentFetches: 8
  timeoutMs: 15000
  totalDeadlineMs: 45000
  respectRobotsTxt: true
  chunkSize: 480                # tokens
output:
  markdown: true
  maxPassageChars: 1500
logging:
  level: warn

interface ResearchResult {
  query: string; queries: string[];        // the query + expansions actually used
  passages: Passage[];                     // ranked; each: text, url, title, score (0–1), cosine?, bm25?,
                                           //   rerankScore?, chunkIndex, startOffset, endOffset, publishedAt?,
                                           //   fetchedAt, matchedQueries, citation "[n] Title — url"
  sources: SourceSummary[];                // one per page: status ok|failed|cached, chunks, bestScore, passageIndices, failure?
  failures: Failure[];                     // per-URL / per-stage problems with machine codes (never thrown)
  stats: { search, ingest, embed, retrieve, totalMs, warnings };   // timings + counts per stage
  markdown?: string;                       // the pre-rendered version above
  degraded?: 'search_only' | 'partial';    // e.g. every fetch failed → search snippets returned instead
}

git clone https://github.com/rthomas24/web-vector
cd webvector
npm install                     # installs all workspaces (~1 min; includes the optional model runtime for tests)
npm run build                   # tsdown → packages/*/dist

# use the local build
node packages/cli/dist/cli.js search "reciprocal rank fusion" --stats
node packages/mcp/dist/bin.js                     # MCP server on stdio
node packages/mcp/dist/bin.js --http --port 3333  # …or HTTP

# point an MCP client at the local build
claude mcp add webvector-dev -- node /absolute/path/to/webvector/packages/mcp/dist/bin.js

# quality gates
npm test                        # unit tests, offline (mocked HTTP), ~5 s
npm run test:live               # real network + local model + MCP stdio round-trip (~20 s)
npm run lint                    # biome
npm run typecheck               # TypeScript 7

import { customSearchProvider, registerSearchProvider, WebVector } from 'webvector';

const myIndex = customSearchProvider('my-index', async (query) => [
  { url: 'https://…', title: '…', snippet: '…' },
]);
new WebVector({ search: { instance: myIndex } });
// or: registerSearchProvider('my-index', (opts) => new MyProvider(opts));  → search.provider: my-index

research(query)
  1. search      provider chain (DuckDuckGo → fallbacks) → dedupe by canonical URL → domain filters → top N
  2. ingest      concurrent, polite fetch → HTML (Readability→Markdown) | PDF | text → page cache
  3. chunk+embed markdown-aware recursive chunks with heading breadcrumbs → content-hash dedupe → embed (batched, cached)
  4. retrieve    query + expansions → vector top-k lists + BM25 top-k lists → weighted RRF → cosine cutoffs
                 → near-duplicate removal → per-source cap → MMR → optional rerank → top-k
  5. format      passages with citations, sources, failures, per-stage stats, Markdown