Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
Agentdiet is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Strips 85-97% of HTML bloat into clean Markdown, <200-token skeletons, or BM25 excerpts via MCP.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agentdiet-mcp https://agentdiet-72343955726.us-central1.run.app/mcp
# 2 — ask your agent for something these tools do
# distill_webpage, recon_webpage_skeleton, extract_structured_data and 16 more
Agentdiet costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http agentdiet-mcp https://agentdiet-72343955726.us-central1.run.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Strips 85-97% of HTML/JS/CSS noise from a URL or HTML string. Supports modes: 'markdown', 'structured', 'skeleton', 'budget' (BM25).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Target URL (or builtin://stripe-docs) |
| html | string | no | Optional raw HTML string |
| mode | string | no | — |
| query | string | no | BM25 focus query for budget mode |
| max_tokens | integer | no | Token cap for budget mode |
Returns a <200-token structural outline of any webpage with section headings and token counts before committing context window budget.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Target webpage URL |
| html | string | no | Optional raw HTML string |
Extracts JSON-LD schemas, OpenGraph tags, HTML tables parsed as JSON objects, and code blocks from any webpage URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Target webpage URL |
| html | string | no | Optional raw HTML string |
Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router (0.01 USDC via x402): Single-connection meta-router indexing 500+ MCP servers & A2A tools with 85% token compression and Prompt-Guard firewall.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Capability search query (e.g. 'context compression', 'github security', 'sec filings', 'company enrichment') or endpoint URL to verify |
A2A Indirect Prompt-Injection & Jailbreak Firewall (0.005 USDC via x402): Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Untrusted text, HTML, or tool output to scan for hidden prompt injection or jailbreak payloads |
Deterministic A2A Broken-JSON Repair & Schema Validator (0.002 USDC via x402): Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes) so multi-agent pipelines never crash.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| raw_json | string | yes | Malformed, truncated, or markdown-wrapped JSON string to deterministically repair |
Zero-Bloat A2A Live Web Search & Tech News Grounding (0.01 USDC via x402): Executes live Google News RSS + HackerNews Algolia search queries and returns clean, token-pruned results with zero ad bloat.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search query for live news, technical articles, and web results |
Automated /llms.txt & Agent Documentation Context Compiler (0.015 USDC via x402): Crawls any documentation or SaaS site and compiles a standards-compliant /llms.txt manifest and JSON-LD schema bundle.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Website URL to crawl and generate a ready-to-consume /llms.txt manifest for |
Coding Agent GitHub Repo, Dependency & License Security Auditor (0.01 USDC via x402): Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-chain security before code execution.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | yes | GitHub repository in owner/name format (e.g. modelcontextprotocol/servers or langchain-ai/langgraph) |
B2B Company, Tech Stack & Contact Lead Enrichment (0.02 USDC via x402): Extracts verified emails, social links, 40+ tech stack signals, pricing tiers, and company summary for GTM & research agents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Company domain name or URL (e.g. stripe.com, linear.app) to enrich |
SEC EDGAR Public Company 10-K/10-Q Financial Intelligence (0.02 USDC via x402): Resolves all 10,000+ US public stock tickers to SEC CIK numbers, recent 10-K/10-Q/8-K filings, and entity metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ticker | string | yes | Public stock ticker symbol (e.g. NVDA, MSFT, AAPL, PLTR) |
Domain OSINT, TLS Certificate & Security Headers Recon (0.01 USDC via x402): Inspects live IPv4/IPv6 DNS resolution, TLS certificate issuer/expiry, and HTTP security grade.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Target domain name (e.g. anthropic.com, openai.com) for DNS, TLS certificate, and security header OSINT |
B2A Email Deliverability, MX, SPF & DMARC Verifier (0.005 USDC via x402): Validates email syntax, disposable/burner provider status, role accounts, and live DNS MX/SPF/DMARC records.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email address to validate for syntax, MX deliverability, and disposable risk |
ArXiv AI/CS Paper Search & Structured Token-Diet Digest (0.01 USDC via x402): Queries ArXiv for AI/CS/math papers and returns structured abstracts, authors, PDF links, and BibTeX.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | ArXiv paper ID (e.g. 2308.11432) or research topic search query |
E-Commerce & SaaS Product Catalog / Price Extractor (0.02 USDC via x402): Extracts normalized product catalogs, live prices, variants, and availability from online stores.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| store_url | string | yes | Shopify or e-commerce store URL to extract structured product & pricing data from |
A2A, MCP & HTTP 402 Endpoint SLA Compliance Auditor (0.01 USDC via x402): Audits any remote agent or MCP URL for JSON-RPC compliance, latency SLA, OpenAPI schema, and HTTP 402 settlement headers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Target A2A, MCP, or x402 service URL to audit for protocol compliance |
Base EVM & Solana Smart Contract Security Scanner (0.02 USDC via x402): Audits any Base EVM 0x contract or Solana SPL Mint for proxy patterns, GoPlus honeypot flags, and freeze authority.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | 0x EVM contract/wallet address on Base or Solana Base58 SPL Mint address |
DEX Liquidity, Slippage & Orderflow Audit API (0.015 USDC via x402): Fetches live DexScreener liquidity pools, FDV, 24h volume, and 1h buy/sell orderflow pressure.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| token | string | yes | Token contract address or symbol (e.g. USDC, WETH, AERO) on Base/Solana/Ethereum |
Returns the calling agent's remaining free quota, USD balance, and total tokens saved.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | no | — |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Agentdiet or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Agentdiet can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.