data-ai MCP Server
Agent OS | Multi-provider concurrent dispatch | Self-improving error memory | Pluggable tool extensions | Sandbox execution
Discovered via agent-topic:ai-agent and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Read a text, PDF, DOCX, PPTX, CSV/TSV, or image file.
Search Google News RSS and return article titles, summaries, links.
Write content to a file, overwriting if it exists.
Attach interactive TUI; forks daemon (HTTP + Discord + Telegram + scheduler + summary cron) if not running.
Fetch a web page and return its content as Markdown.
Description
Search the web via DuckDuckGo Lite; returns top 10 results.
Search available tools by keyword and inject matches into the request.
Invoke one external CLI agent (codex / copilot / claude / gemini) for a second opinion.
Replace an exact string match inside a file.
中文
Evaluate a mathematical expression and return the exact result.
Persist a tool-error record for future retrieval.
Fetch a skill's reference material by exact name.
Bind an existing scheduler skill to fire once at a specific time (`+5m` / `HH:MM` / `YYYY-MM-DD HH:MM` / RFC3339).
✅
Transcribe a YouTube video with timestamps. *(gemini needed)*
List authorized Discord channels (id + name). *(discord needed)*
Search the session's past messages by keyword and semantic similarity.
Bind an existing scheduler skill to a recurring 5-field cron expression.
TypeScript
✅ bubbletea
Go (static binary)
List directory entries; `recursive=true` walks subtree files.
Transcribe a local audio / video file (ogg, mp3, wav, m4a, flac, aac, mp4, mov, webm, mpeg, 3gp, …) up to 20 MiB. *(gemini needed)*
Apache 2.0
✅ native daemon
Description
TypeScript
✅
Detail
Find files matching a glob pattern within a directory.
Send an HTTP request to a specified URL.
MIT
✅ native daemon
Overwrite the rendered HTML page for the current session; tabs auto-reload.
List all currently available built-in and dynamically loaded tools.
Run a subtask in an internal subagent session and return its final text.
OpenAI
❌
Fetch a web page and save its content to a local file.
Generate an image via gpt-image-2 (size & quality picked by user). *(codex needed)*
NousResearch
**Agenvoy**
List authorized Telegram chats (id + name). *(telegram needed)*
Cross-review a completed result across all available external agents in parallel.
✅
Send an HTML-formatted message to an authorized Telegram chat by chat_id. *(telegram needed)*
Ask the user one or more questions and return their answers.
✅
0
Search file contents by RE2 regex within a directory.
Run a binary with argv; returns combined stdout/stderr.
Query Yahoo Finance quotes and K-line (OHLCV).
Return the Telegram HTML formatting reference (allowed tags, escape rules, file/voice markers). *(telegram needed)*
Send a markdown-formatted message to an authorized Discord channel by channel_id. *(discord needed)*
Semantically search past tool-error records; hits refresh 3-month TTL.
Return the Discord markdown formatting reference (allowed markdown, special tokens, file/voice markers). *(discord needed)*
Fetch a prior tool-error record by hash.
Prompt the user for a secret with masked input and persist to the system keychain.
Review a result against the original input and return issues and improvements.