"DeepSeek JSONL阅读能力" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
mumo is a remote MCP server for multi-model deliberation. Your agent sends a question to models from different labs — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more — and gets back their full responses plus typed cross-model reactions. The participating models react to each other directly and explain, in their own words, what they agree with, challenge, or want to explore further. Agents can run a deliberation with `create_deliberation`, wait for results with `wait_for_round`, and steer follow-up rounds with `append_round` using structured signals like KEEP, EXPLORE, CHALLENGE, CORE, and SHIFT. Built for architecture, plan/spec review, strategy, and pre-launch pressure tests. Free tier available. API key required.
Free 1-line peer-to-peer (P2P) mobile app cross-promotion for Android (Jetpack Compose), iOS (SwiftUI), Flutter, React Native, and Hybrid WebView apps. Delivers zero-dependency single-file SDKs, audience matching, and integration verification with zero ad spend, zero user tracking, and zero GDPR popups.
Which LLM should I use for this task? Ask in plain words and get the models that score best on the matching benchmark board, within your price, context window and open-weights limits. Covers 400+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, Mistral and more, with benchmark scores (coding, agentic, reasoning, math, knowledge, design) and API list prices per million tokens, updated daily. Tools: recommend_model, get_leaderboard, compare_models, get_model, get_prices, list_categories. Free, no API key, data under CC BY 4.0. Docs: https://llmbenchmark.ai/api
OpenAny is the B2A (business to agent) marketplace. Add one MCP endpoint, https://mcp.openany.si, and your agent can find and use 3,200+ APIs and 168+ AI models. APIs cover social and content (X, TikTok and more), SEO, search and scraping (DataForSEO, Serper, Tavily), crypto and on-chain data (CoinGecko, DefiLlama, DexScreener, Hyperliquid, Polymarket), company and lead data (Hunter, Crustdata, QCC), finance and macro (FRED, Financial Datasets), and legal (PKULaw). Models include chat and reasoning (GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax), image (Midjourney, FLUX, Nano Banana, Seedream, GPT Image), video (Veo, Kling, Seedance, Hailuo, Wan) and audio. Searching and checking prices is free with no key. You only need an OpenAny API key to run a call, and you pay per call.
Zero-auth Notary & AST: RM(1,3), RFC 6962, W3C VC 2.0, ROS 2, 3-Level Mind & A2A-MCP Bridge.
Browse CommerCentr product catalogs and use scoped content and SEO tools.
C engineering review, delivered per API call as an atom service on Conduit Atoms.
JSON schema design check: schemas, canonical form, versioning and parse safety, per call.
Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.
Short links + QR codes for AI agents (EN/中文). Public beta. Docs public; most tools need an account.
Official rules, version per result. SAF-T, SEPA, ISO 20022, DAC7 checks; CBAM and XBRL web tools.
Ultra-low latency edge MCP server and token optimizer. Reduces LLM context costs by 60-99% via AST code skeletons, homogeneous JSON pruning, and stream healing.
Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes).
Developer fixes, free skills, browser tools and scoped technical services over MCP.
Audits any live MCP server URL or GitHub repo on Glama's 6-dimension TDQS rubric and compiles dro.
Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, unquoted keys).
Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.
AI-assisted academic LaTeX workbench: import projects from zip/Git, read and edit files, compile to real PDFs with structured error fixes, SyncTeX round-trip, and paper library search & reading.
A shared immune system for autonomous AI agents. Provides herd immunity to known runtime crashes by serving deterministic, cryptographically signed patches in sub-50ms.
Feature-request board for software teams: users vote, your coding agent pulls the top request as a spec over MCP, voters get emailed when it ships.
Browser support for web features, live from caniuse. From which version, and is it safe to ship?
Read-only MCP for Japanese business systems: APIs, authentication, integration routes and live status, each with source URL and survey date. Website: https://renkeimap.jp Systems: https://renkeimap.jp/system Live status and outages: https://renkeimap.jp/status Integration tools: https://renkeimap.jp/tool AI and automation tools: https://renkeimap.jp/ai Guides: https://renkeimap.jp/guide How to use this MCP: https://renkeimap.jp/guide/learn/our-mcp-server 日本の業務システムの API・認証・接続方式・稼働状況を、出典と調査日つきで返す読み取り専用 MCP(IT連携マップ)。 システム一覧:https://renkeimap.jp/system 稼働状況・障害情報:https://renkeimap.jp/status 記事・ガイド:https://renkeimap.jp/guide この MCP の使い方:https://renkeimap.jp/guide/learn/our-mcp-server 訂正窓口:https://renkeimap.jp/request
Renders dashboards, forms and tables inline in the chat as Angular Material components (MCP App).
GW1 build compiler: skill data, template code encode/decode, validation, hero roster. Read-only.
Autonomous 0-DRC PCB Routing, RF/DFM Pre-Flight & KiCad MCP Server (calligraphyeda.com).
Pay-per-call x402 tools (USDC/Base): JSON validate, CSV, diff, PDF, Mexican RFC/CURP/CLABE.
On-demand access to amCharts 5 docs, code examples, and API reference
dBW to watts, number discarded
Small public utility for autonomous clients.
KOI8-U high-bit band, bytes discarded
C string escape count, input discarded
One section in, one section out — on Markdown/GEML files, bad writes refused.
z-base-32 charset, input discarded
JSONL object-line count, bodies discarded
UTF-1 signature bytes, input discarded
PascalCase token count, value discarded
Whether a zone name looks like DST-aware
UTC millisecond 0-999 band
comma-separated token count, value discarded
colon-separated token count, value discarded
Angstroms to meters, number discarded
Picometres to meters, number discarded
ISO-8859-1 byte count, text discarded
UTC first day of the current quarter
Python string escape count, input discarded
Cubic feet/min to m3/s, number discarded
Honest library picks for coding agents in 25-360 tokens. Tells your agent what NOT to install.
UTC second day of the current month
Early-Data 1 token, value discarded
C octal-escape count, input discarded
Gregorian Y-M-D shape, value discarded
UTC nanosecond 9-digit band
UTC midpoint day of the current quarter
Fathoms to meters, number discarded
Liters/min to liters/s, number discarded
multibase z-prefix, value discarded