Toolcall vs Agentreader MCP

A side-by-side look at the Toolcall and Agentreader MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Toolcall logoToolcallFinance & Fintech · Remote HTTP/SSE30 pay-per-call APIs for AI agents: compliance, trade, safety, web, data. USDC on Base via x402.53GoodAuth: not declaredAgentreader MCP logoAgentreader MCPFinance & Fintech · Local subprocess (stdio)11 pay-per-call web tools for AI agents, auto-paid in USDC on Base via x402. No API keys.52GoodAuth: not declared

Verdict: choose Toolcall for finance & fintech work over a hosted endpoint; choose Agentreader MCP for finance & fintech as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Toolcall logoChoose Toolcall when

  • You need dedicated capabilities in the Finance & Fintech domain.
  • You prefer a remote HTTP/SSE transport.
  • You want tools like crypto-gas, fx-rates, domain-check.
Explore Toolcall

Agentreader MCP logoChoose Agentreader MCP when

  • You need dedicated capabilities in the Finance & Fintech domain.
  • You prefer a local stdio subprocess transport.
  • You have the keys it needs: AGENTREADER_PRIVATE_KEY.
  • You want tools like read_page, page_metadata, clean_html.
Explore Agentreader MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecToolcall logoToolcallAgentreader MCP logoAgentreader MCP
CategoryFinance & FintechFinance & Fintech
Quality signal53/100 · Good52/100 · Good
Install commandConfirmedConfirmed
TransportRemote HTTP/SSELocal subprocess (stdio)
AuthNot declaredNot declared
PricingNot declaredNot declared
Required env varsNone listedAGENTREADER_PRIVATE_KEY
Verified ownerCommunity listingCommunity listing
GitHub stars00
Directory activity 0 views 0 installs 0 upvotes 3 views 0 installs 0 upvotes
Tools2013

Tools & capabilities

Toolcall tools 20

  • crypto-gasCurrent gas price and latest block for Base or Ethereum mainnet, straight from public RPC. Fresh within 15 seconds. JSON response. [Paid: $0.002 USDC per call via x402 on Base; the calling client pays automatically.]
  • fx-ratesForeign exchange reference rates from the European Central Bank. Base currency plus optional symbols filter. Updated daily on ECB schedule. JSON response. [Paid: $0.002 USDC per call via x402 on Base; the calling client pays automatically.]
  • domain-checkDue-diligence check on any domain: registration age via RDAP, registrar, DNS posture (A/MX/NS), SPF and DMARC presence, SSL certificate history, and risk flags like newly-registered or no-mail-setup. One call, one JSON verdict. [Paid: $0.008 USDC per call via x402 on Base; the calling client pays automatically.]
  • email-validateEmail verification and deliverability check without sending anything: syntax, MX records, disposable-domain detection (121k+ known domains), role-account and free-provider flags. JSON verdict with a bounce/deliverability risk level. Validate emails for signup fraud prevention, list hygiene and lead qualification. [Paid: $0.004 USDC per call via x402 on Base; the calling client pays automatically.]
  • news-searchRecent news headlines for any company, topic or query: deduplicated titles with source, link and publish date from a broad news index. Window configurable 1-30 days. JSON response. [Paid: $0.01 USDC per call via x402 on Base; the calling client pays automatically.]
  • youtube-transcriptFull plain-text transcript of a YouTube video, de-duplicated and cleaned from the captions. Accepts a video id or URL. Ideal for feeding video content to LLMs. JSON response. [Paid: $0.01 USDC per call via x402 on Base; the calling client pays automatically.]
  • web-searchKeyless web search for agents: pass a query, get a concise web-grounded answer plus the top source results (title, URL, snippet). Live web access, no API key or account needed. JSON response. [Paid: $0.008 USDC per call via x402 on Base; the calling client pays automatically.]
  • brand-visibilitySee what AI models say about a brand right now. Runs category and reputation prompts across multiple AI engines (one web-grounded), then reports whether the brand is mentioned, its position vs competitors, sentiment, the exact descriptors used, gaps, and concrete recommendations. JSON report. [Paid: $0.25 USDC per call via x402 on Base; the calling client pays automatically.]
  • screenshotFull-fidelity screenshot of any public web page, captured by a real Chrome browser. Viewport or full-page, configurable width. Returns a base64 PNG. JSON response. [Paid: $0.015 USDC per call via x402 on Base; the calling client pays automatically.]
  • readerTurn any public web page, including JavaScript-heavy ones, into clean readable markdown (or text/html) with title and byline. Rendered by a real browser then stripped to the main content. Ideal for feeding pages to LLMs. JSON response. [Paid: $0.006 USDC per call via x402 on Base; the calling client pays automatically.]
  • chem-safetyFull safety profile for any chemical by CAS number or name: GHS hazard classification (signal word, pictograms, H-statements, P-codes), first-aid measures for inhalation/skin/eye/ingestion, fire-fighting guidance, UN transport number, PPE, and CAMEO reactivity profile. Sourced live from PubChem (NIH) authoritative annotations. JSON response. [Paid: $0.03 USDC per call via x402 on Base; the calling client pays automatically.]
  • chem-compatCan chemical A be safely mixed or stored with chemical B? Pass two CAS numbers or names. Returns a verdict (incompatible / caution / no_known_hazard), the reason, expected effects (gas evolution, heat, fire, toxic fumes) and confidence, from expert reasoning over PubChem GHS data and CAMEO-derived reactivity profiles. JSON response. [Paid: $0.03 USDC per call via x402 on Base; the calling client pays automatically.]
  • +8 more on the listing page

Agentreader MCP tools 13

  • read_pageWeb page → clean LLM-ready markdown article
  • page_metadataTitle, OpenGraph, Twitter cards, JSON-LD, headings
  • clean_htmlRaw HTML → markdown
  • pdf_textPDF URL → full text (up to 25 MB)
  • parse_feedRSS/Atom/RDF feed → normalized JSON items
  • parse_sitemapXML sitemap → URL list
  • extract_linksPage link graph with anchor text
  • dns_lookupDNS records with TTLs
  • screenshotReal-browser PNG screenshot
  • summarizeAI summary of URL or text (dense, factual)
  • extract_structuredPage/text → JSON matching **your** JSON Schema
  • sanctions_screenOFAC SDN + Consolidated screening: fuzzy transliteration-aware name match or crypto-address lookup, with verdict + list provenance
  • +1 more on the listing page

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Toolcall

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "toolcall": {
      "url": "https://toolcall.click/mcp"
    }
  }
}

Agentreader MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "agentreader-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentreader-mcp"
      ],
      "env": {
        "AGENTREADER_PRIVATE_KEY": "YOUR_AGENTREADER_PRIVATE_KEY_HERE"
      }
    }
  }
}

Frequently asked questions

Toolcall is categorized under Finance & Fintech and uses a remote HTTP/SSE transport. Agentreader MCP belongs to Finance & Fintech and uses a local stdio subprocess. Pick Toolcall for finance & fintech work and Agentreader MCP for finance & fintech.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Toolcall has no declared pricing — check the project's own site. Agentreader MCP has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add toolcall and agentreader-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Toolcall has a quality signal of 53/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Agentreader MCP has 52/100 (Good) with 3 views, 0 installs and 0 GitHub stars.