"Methods for Categorizing Images" matching MCP servers:

Generate and edit images with GPT Image 2.5 for $0.029 each, inside Claude, Cursor or any MCP client. A free you.bot API key comes with 50 credits (about 17 images) and needs no card.

A client-side MCP proxy that injects OAuth 2.0 bearer tokens or API keys into MCP requests, enabling MCP clients to connect to OAuth/API-key-protected MCP servers like Amazon Bedrock AgentCore Gateway. It automatically fetches and refreshes credentials using AgentCore Identity or static values.

An MCP server that lets Codex generate, edit, and display images via the Wawapi image API using only text content blocks, local file paths, and Markdown, without requiring native image support from the model API.

A locally runnable stdio MCP server for Fortrip hotel search, live room rates, hotel details, trip planning and booking payment links. Uses a Fortrip CLI token or saved CLI login; payments are completed by the user on Fortrip and Stripe.

Provides AI agents with 0–100 marketplace-evidence scores for retail product listings, enabling inspection and comparison of products across Amazon, Walmart, Target, and Best Buy using native retailer IDs.

The open-source, self-organizing memory for all your AI tools. Persistent memory over MCP (remember, recall, observe): background agents extract entities, resolve conflicts, and keep cited syntheses current in an append-only, encrypted, single-tenant vault.

Checks live x402 routes across Base, Solana, and Algorand before agents spend. $0.003 USDC settles only for a valid live eligible route; normal typed misses are not settled. Free preview and validate tools. Seller payment is separate; the agent keeps its wallet. Optional signed route-binding receipts support buyer-side checks.

Agent trust & data safety MCP: PII/secret redaction, email validation, sanctions screening, and OSV vulnerability checks for AI agents.

Enables agents to inspect web pages for Cloudflare Turnstile challenges without an API key, and clear Turnstile or WAF challenges using a SolveGate API key.

Rug pull risk scores and on-chain forensics for memecoins on Solana, Ethereum, Base and Robinhood Chain - launch-bundle detection, funding-origin tracing, deployer history, insider networks and whale flow. 15 read-only tools.

Dynamic multi-agent debate MCP server for structured argumentation and reasoning among AI agents.

Brazilian foreign trade from MDIC/ComexStat -- exports and imports since 2000 by HS code (SH4/SH6/NCM) and partner country, in USD FOB and kilograms -- plus crop production, supply-and-demand balances, climate readings and commodity forecasts for hubs such as soybean, coffee and beef. 15 read-only tools, remote at https://mcp.kyrodata.com/mcp; official registry com.kyrodata/kyrodata.

Hourly electricity grid carbon intensity (gCO2eq/kWh) for 45 zones across Europe, the US and Great Britain, computed from ENTSO-E, EIA and NESO generation data. Four read-only tools; every value carries its interval timestamp and how stale it is. No API key, no account.

Local MCP decision gate for AI agents and CI/CD: check candidate actions against owner-controlled policy and proposal-bound evidence. Three read-only tools report admissible options, missing evidence, and SHA-256 receipts. No selection, execution, or DeltaX API key.

Enables MCP clients like Claude Desktop and Claude Code to drive a real browser with SeleniumBase automation. Offers three variants: WebDriver-based general automation, Pure CDP Mode for bot-detection bypass, and a broad SB() API with MFA and downloads.

Send and read SMS through your own Android phone via textbee.dev, the open-source SMS gateway. Three tools for Claude, Cursor, and any MCP client: send_sms, get_messages (replies, verification codes, delivery status), list_devices. Self-hosted friendly.

Pre-computed financial market intelligence for AI agents. Stocks, crypto, and ETFs.

Local-first memory for coding agents. Discovers the memory, instructions, and rules Claude Code, Codex, and Cursor already wrote on your machine, combines them into one canonical Markdown tree, and serves grounded, cited recall through tools like ask_memory and canonical_memory.

Enables AI assistants to search Bangladesh's automotive parts catalogue and vehicle listings in BDT, compare cars, check auction status, and look up part or listing details. It also supports buying guides and preparing a purchase handoff for a human buyer, with optional authenticated ordering tools.

An MCP server for querying the FDSN Web Service Event APIs of multiple seismological datacenters and retrieving earthquake information as JSON.

Search Vascue's public healthcare-operations documentation: AI front desk for clinics, provider-side insurance claims automation, Cliniko integration, security. Public content only.

Free VOP (Verified Output Protocol) verification for AI agent outputs — score any output 0-100 and get a PASS/PARTIAL/FAIL verdict. No account, no escrow, no financial transaction of any kind.

Enables AI agents to check a list of websites by running an Apify Actor through one tool, returning per-site tech stack, on-page SEO issues and score, robots.txt rules for AI crawlers, sitemap, llms.txt presence, and an AI-readiness score. Supports local stdio operation with an Apify token for tool calls.

MCP server that lets AI assistants like Claude or Cursor extract structured data (e.g., invoices) from images and PDFs via Vision API, with tools for analysis, questions, and preset management.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

Provides a local MCP server that exposes the check_prompt_injection tool to MCP clients, letting agents scan untrusted text (web pages, documents, tool outputs, emails) for prompt injection before passing it to another LLM.

MCP server providing deterministic cost anomaly detection for cloud billing and auditable architecture risk scoring, enabling AI agents to identify waste and risk with explainable rules.

An MCP server that uses Xiaomi MiMo v2.5 multimodal model to provide image recognition capabilities (description, multi-image analysis, OCR, and image info validation) for text-only main models like deepseek-v4-flash, accepting local paths, URLs, file://, and base64 data inputs.

MCP server for searching Korean public procurement bid notices (나라장터) using natural language.

Query verified pricing, aggregated user ratings, feature comparisons, and category rankings for 508+ SaaS, AI, and security tools across 45 categories. No API key required - install with npx @comparedge/mcp-server