Loading…
Pay-per-call AI API marketplace with 47 endpoints — OCR, TTS, LLM chat, image generation, weather, and crypto pricing — paid via x402 USDC micropayments on Base.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The GoldBean MCP Server MCP server exposes 51 tools, focused primarily on database and communication capabilities. Its published description reads: "Pay-per-call AI API marketplace with 47 endpoints — OCR, TTS, LLM chat, image generation, weather, and crypto pricing — paid via x402 USDC micropayments on Base". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates GoldBean MCP Server D+ — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check GoldBean MCP Server's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add GoldBean MCP Server to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://goldbean-api.xyz/sseStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Checks the health status of the GoldBean API service. Use to verify service availability before making other API calls or for uptime monitoring. Returns JSON with status, uptime, version, and active e
Recognizes text in images using Baidu General OCR engine. Use when you need to extract text from photos, screenshots, or scanned documents. Supports Chinese, English, and multi-language text. Returns
Performs high-accuracy text recognition on images using Baidu Accurate OCR engine. Use when standard OCR results are insufficient and higher precision is needed for complex or low-quality images. Retu
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: baidu_vision_chat
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
images through conversational interface using Baidu vision-language model.RecommendationRemove side-channel parameters; constrain tool inputs.
tool: baidu_video_gen
A tool description tries to alter the model’s use of another tool.
generation (use baidu_video_query to check status). Pricing: $0.08/call.RecommendationDescriptions must describe only their own tool.
tool: baidu_video_query
A tool description tries to alter the model’s use of another tool.
e after calling baidu_video_gen to check if the video is ready for download. ReRecommendationDescriptions must describe only their own tool.
tool: register
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "password"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: check_credits
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
AWS's official fully managed remote server that provides real-time access to comprehensive AWS documentation, API references, troubleshooting guides, and architectural guidance across multiple knowledge sources including What's New posts, Builder Center content, blog posts, and Well-Architected frameworks for building applications, managing infrastructure, and learning AWS services through natural language queries.
Search live events, conference weeks, host cities, venues, and artist tour schedules.
Live verifiable on-chain data for the $BOBAI token on BNB Chain.
Identity certification, public registry, reputation scoring, and x402 micropayments for AI agents built on Base and Solana.
Search 11M+ products across SG, SEA, and US. Agent-native catalog for AI shopping agents.
Extracts table structure and text from images using Baidu Table OCR. Use when you need to parse tabular data from screenshots or scanned spreadsheets. Returns JSON with table cells, row/column structu
Extracts information from Chinese ID cards (front and back) using Baidu ID Card OCR. Use to automate identity verification or form filling from ID card photos. Returns JSON with name, gender, national
Recognizes handwritten text in images using Baidu Handwriting OCR. Use to digitize handwritten notes, forms, or signatures. Returns JSON with recognized handwritten text, word bounding boxes, and conf
Detects and decodes QR codes and barcodes in images using Baidu QR Code OCR. Use to extract information from QR codes, barcodes, or QR-based payment codes. Returns JSON with decoded text content, code
Extracts bank card number and type from images using Baidu Bank Card OCR. Use to automate payment form filling or card information digitization. Returns JSON with bank card number, card type (debit/cr
Extracts information from Chinese business license images using Baidu Business License OCR. Use to automate company registration data entry or business verification workflows. Returns JSON with compan
Extracts text from web images using Baidu Web Image OCR. Optimized for images with complex backgrounds, watermarks, or non-standard fonts commonly found online. Returns JSON with recognized text, word
Performs OCR using DeepSeek vision model for complex document understanding. Use when traditional OCR fails on complex layouts, mixed content, or documents requiring contextual understanding. Returns
Uses PaddleOCR-VL vision-language model for advanced document understanding and text extraction. Use for complex documents with tables, formulas, stamps, or mixed layouts that require visual-language
Performs custom OCR using Qianfan platform template-based recognition. Use when you have a specific document template configured on Qianfan and need structured field extraction. Returns JSON with temp
Converts text to natural-sounding speech using Baidu Text-to-Speech engine. Use to generate audio for content, accessibility features, or voice assistants. Supports Chinese and English with multiple v
Converts speech audio to text using Baidu Automatic Speech Recognition. Use to transcribe voice recordings, build voice commands, or enable speech-to-text features. Supports Chinese and English audio.
Generates text responses using Baidu large language models (ERNIE series). Use for conversational AI, text generation, question answering, summarization, code generation, and reasoning tasks. Returns
Performs deep reasoning tasks using Baidu ERNIE with extended thinking capability. Use for complex multi-step reasoning, mathematical proofs, logical analysis, and tasks requiring deliberate thought c
Analyzes images through conversational interface using Baidu vision-language model. Use to ask questions about image content, describe scenes, answer visual questions, or perform image-based reasoning
Translates text between languages using Baidu Translation API. Supports over 20 languages including Chinese, English, Japanese, Korean, French, German, Spanish, Russian, and more. Returns JSON with tr
Performs general image recognition to identify objects, scenes, and concepts using Baidu Image Recognition. Use to tag images, categorize content, or build image search features. Returns JSON with rec
Detects and locates multiple objects in images using Baidu Object Detection. Use to find and count items, build inventory systems, or enable object-based image search. Returns JSON with detected objec
Identifies landmarks and famous locations in images using Baidu Landmark Recognition. Use to tag travel photos, build location-based services, or identify tourist attractions. Returns JSON with landma
Identifies plant species from images using Baidu Plant Recognition. Use for botanical identification, gardening apps, or nature education tools. Returns JSON with plant name, confidence score, and opt
Identifies animal species from images using Baidu Animal Recognition. Use for wildlife identification, pet breed detection, or educational applications. Returns JSON with animal name, confidence score
Identifies dishes and food items from images using Baidu Dish Recognition. Use for food logging, restaurant menu digitization, or dietary tracking apps. Returns JSON with dish name, confidence score,
Detects and identifies brand logos in images using Baidu Logo Recognition. Use for brand monitoring, advertisement analysis, or sponsorship tracking. Returns JSON with logo name, bounding box, and con
Identifies vehicle make, model, and year from images using Baidu Car Recognition. Use for vehicle identification, parking management, or automotive apps. Returns JSON with car brand, model, year, and
Identifies food ingredients and raw materials from images using Baidu Ingredient Recognition. Use for cooking apps, dietary analysis, or grocery identification. Returns JSON with ingredient name and c
Detects and counts vehicles in images using Baidu Vehicle Detection. Use for traffic monitoring, parking lot management, or smart city applications. Returns JSON with vehicle count, types (car, truck,
Detects faces in images and extracts facial attributes using Baidu Face Detection. Use for face analysis, demographic estimation, or photo organization. Returns JSON with face count, bounding boxes, a
Compares two face images to determine if they belong to the same person using Baidu Face Comparison. Use for identity verification, duplicate account detection, or photo matching. Returns JSON with si
Analyzes human body attributes in images using Baidu Body Analysis. Use for crowd analytics, retail analytics, or fitness applications. Returns JSON with body count, bounding boxes, and attributes (ge
Detects and recognizes hand gestures in images using Baidu Gesture Recognition. Use for touchless interfaces, sign language translation, or interactive applications. Returns JSON with detected gesture
Enhances image quality through denoising, dehazing, and clarity improvement using Baidu Image Enhancement. Use to improve low-quality photos, remove haze from landscape images, or enhance document sca
Generates images from text descriptions using Baidu AI image generation model. Use to create illustrations, concept art, marketing visuals, or creative content from text prompts. Returns JSON with bas
Edits images using text instructions with Baidu AI image editing model. Use to modify existing images, add/remove objects, change styles, or apply transformations via natural language. Returns JSON wi
Generates videos from text descriptions using Baidu AI video generation model. Use to create short video clips, animations, or motion graphics from text prompts. Returns JSON with task ID for async vi
Queries the status and result of an async video generation task. Use after calling baidu_video_gen to check if the video is ready for download. Returns JSON with task status (pending, running, success
Performs general natural language processing tasks using Baidu NLP engine. Use for lexical analysis, word segmentation, part-of-speech tagging, and basic text understanding. Returns JSON with tokenize
Analyzes sentiment and emotional tone of text using Baidu Sentiment Analysis. Use for brand monitoring, customer feedback analysis, or social media sentiment tracking. Returns JSON with sentiment clas
Generates concise summaries of long text using Baidu Text Summarization. Use to create article abstracts, news digests, or content previews. Returns JSON with summary text and compression ratio. Prici
Detects and corrects spelling, grammar, and punctuation errors in Chinese text using Baidu Text Correction. Use for proofreading, content quality assurance, or writing assistance. Returns JSON with co
Extracts key phrases and keywords from text using Baidu Keyword Extraction. Use for content tagging, SEO optimization, or document indexing. Returns JSON with ranked keywords, weights, and relevance s
Generates word-level vector embeddings using Baidu Word Embedding. Use for semantic similarity calculation, word clustering, or as input features for downstream NLP models. Returns JSON with word vect
Generates dense vector embeddings for text using Baidu Embedding model. Use for semantic search, document clustering, recommendation systems, or RAG (Retrieval-Augmented Generation) pipelines. Returns
Reranks documents by relevance to a query using Baidu Reranker model. Use to improve search result quality, refine RAG retrieval, or reorder candidate documents. Returns JSON with reranked document in
Reviews text content for spam, abuse, profanity, and policy violations using Baidu Text Moderation. Use for user-generated content filtering, comment moderation, or compliance checking. Returns JSON w
Reviews image content for inappropriate, violent, or policy-violating material using Baidu Image Moderation. Use for user-uploaded image filtering, content compliance, or platform safety. Returns JSON
Predicts protein 3D structure from amino acid sequence using Baidu HelixFold. Use for bioinformatics research, drug discovery, or protein engineering. Returns JSON with predicted structure (PDB format
Registers a new GoldBean API account. Use to create an account for accessing paid API endpoints. Returns JSON with user ID, API key, and initial free credits (100 credits = 100 calls). Pricing: Free.
Checks remaining API credits and usage statistics for a GoldBean account. Use to monitor usage, check remaining free tier calls, or verify subscription status. Returns JSON with remaining credits, use