Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/good-boy4069/Deepseek-omnimodalWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/good-boy4069/deepseek-omnimodal/omnimodal-recognize)<a href="https://agentmods.dev/mcp/good-boy4069/deepseek-omnimodal/omnimodal-recognize"><img src="https://agentmods.dev/badge/mcp/good-boy4069/deepseek-omnimodal/omnimodal-recognize/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/good-boy4069/deepseek-omnimodal/omnimodal-recognize"><img src="https://agentmods.dev/badge/mcp/good-boy4069/deepseek-omnimodal/omnimodal-recognize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
omnimodal-recognize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"omnimodal-recognize": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"--project",
".",
"omnimodal-recognize"
],
"cwd": ".",
"env_vars": [
"OMNIMODAL_API_KEY",
"OMNIMODAL_PROVIDER",
"OMNIMODAL_BASE_URL",
"OMNIMODAL_IMAGE_MODEL",
"OMNIMODAL_VIDEO_MODEL",
"OMNIMODAL_AUDIO_MODEL_STANDARD",
"OMNIMODAL_AUDIO_MODEL_PRO",
"OMNIMODAL_OCR_MODEL",
"OMNIMODAL_ASR_MODEL",
"OMNIMODAL_OPENAI_THINKING_PARAM",
"OMNIMODAL_ENV_FILE",
"OMNIMODAL_LANGUAGE",
"OMNIMODAL_LOG_LEVEL",
"OMNIMODAL_PROFILES_JSON",
"OMNIMODAL_MODEL_CATALOG_JSON",
"OMNIMODAL_CACHE_USE_TASK",
"OMNIMODAL_CACHE_TTL_SEC",
"OMNIMODAL_CACHE_MAX_ENTRIES",
"OMNIMODAL_MAX_DIMENSION",
"OMNIMODAL_IMAGE_FORMAT",
"OMNIMODAL_JPEG_QUALITY",
"OMNIMODAL_EXTREME_ASPECT_RATIO_LIMIT",
"OMNIMODAL_IMAGE_TIMEOUT_SEC",
"OMNIMODAL_VIDEO_TIMEOUT_SEC",
"OMNIMODAL_AUDIO_TIMEOUT_SEC",
"OMNIMODAL_BATCH_WORKERS",
"OMNIMODAL_BATCH_TIMEOUT_SEC",
"OMNIMODAL_VIDEO_MAX_MB",
"OMNIMODAL_VIDEO_BASE64_MAX_MB",
"OMNIMODAL_VIDEO_DOWNLOAD_MAX_MB",
"OMNIMODAL_VIDEO_FILES_API_TIMEOUT_SEC",
"OMNIMODAL_VIDEO_KEEP_AUDIO",
"OMNIMODAL_VIDEO_WORKERS",
"OMNIMODAL_AUDIO_UNDERSTANDING_MAX_SEC",
"OMNIMODAL_DRAG_WINDOW_MIN",
"OMNIMODAL_DRAG_PATTERNS",
"OMNIMODAL_DRAG_DIRS",
"OMNIMODAL_ALLOWED_OUTPUT_DIRS",
"OMNIMODAL_ALLOW_PRIVATE_URLS"
],
"tool_timeout_sec": 900
}
}What else .mcp.json configures
This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 55 lines scan A f1680c38248b
omnimodal-recognize is an MCP server published in the GitHub repository good-boy4069/Deepseek-omnimodal (4 stars, last pushed 25d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
vision-bridge-mcp
MCP vision proxy v0.2 — fork-merge of mature vision MCPs. Multi-model fallback, compareimages, cache, CLAUDE.md rules for DeepSeek text in VS Code / Claude Code. Runs locally from the vision-bridge-mcp npm package.
watch-skill
MCP server "watch-skill" as configured in oxbshw/watch-skill. Launched with watch-skill serve.
openrouter-multimodal
Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP. Runs locally from the @stabgan/openrouter-mcp-multimodal npm package. Needs 13 environment variables to run.
pdfmux
Self-healing PDF extraction for RAG — #2 of 8 engines on opendataloader-bench (0.903). Flags pages it can't read instead of dropping them, and certifies any extractor's output for silent drops. Verify signed manifests offline, free. Per-page confidence, 7-tool MCP server, LangChain/LlamaIndex loaders. LlamaParse…
r2r
MCP server "r2r" as configured in mm-weber/loremaester. Runs /workspaces/loremaester/mcp-servers/r2r-wrapper/r2r_mcp_wrapper.py with python3. Needs 1 environment variable to run.
vault-graph
MCP server "vault-graph" as configured in mm-weber/loremaester. Runs /workspaces/loremaester/mcp-servers/vault-graph/server.py with python3. Needs 1 environment variable to run.