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/shixinnt/codex-image-context-runtimeInstalling this writes the configuration, not the program: `node` runs a file from the repository, so clone it first and make the path in the command match where you put it.
Wrote 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/shixinnt/codex-image-context-runtime/codex-image-context-runtime-image_context_runtime)<a href="https://agentmods.dev/mcp/shixinnt/codex-image-context-runtime/codex-image-context-runtime-image_context_runtime"><img src="https://agentmods.dev/badge/mcp/shixinnt/codex-image-context-runtime/codex-image-context-runtime-image_context_runtime/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/shixinnt/codex-image-context-runtime/codex-image-context-runtime-image_context_runtime"><img src="https://agentmods.dev/badge/mcp/shixinnt/codex-image-context-runtime/codex-image-context-runtime-image_context_runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
image_context_runtime 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 1mo 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
{
"image_context_runtime": {
"cwd": ".",
"command": "node",
"args": [
"./mcp/server.mjs"
],
"env_vars": [
"OPENAI_API_KEY",
"CODEX_IMAGE_CONTEXT_HOME",
"PLUGIN_DATA",
"CLAUDE_PLUGIN_DATA",
"CODEX_IMAGE_CONTEXT_CONFIG",
"CODEX_IMAGE_CONTEXT_PROVIDER",
"CODEX_IMAGE_CONTEXT_ROOTS",
"CODEX_IMAGE_CONTEXT_IMAGE_MODEL",
"CODEX_IMAGE_CONTEXT_VISION_MODEL"
],
"tool_timeout_sec": 900
}
}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.
- 1mo ago First seen · 21 lines scan A 640363779a41
image_context_runtime is an MCP server published in the GitHub repository shixinnt/codex-image-context-runtime (99 stars, last pushed 2mo ago), licensed Apache-2.0. 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 2026-08-30.
Other mcp servers, from other repositories
mcp-image
AI image generation and editing with prompt optimization and quality presets. Powered by Nano Banana. Runs locally from the mcp-image npm package. Needs 4 environment variables to run.
mindtrain
MCP server "mindtrain" as configured in shigella520/MindTrain. Runs ./scripts/mindtrain_mcp_bridge.py with python3.
neurostack
Token-efficient MCP memory for Markdown vaults. Tiered retrieval, hybrid search, GraphRAG. Runs locally from the neurostack npm package. Needs 1 environment variable to run.
rag-rat
CLI and MCP entrypoint for indexing repositories into local source, graph, history, and memory evidence. Runs locally from the @rag-rat/bin npm package.
mcp-midjourney
MCP Server for Midjourney AI Image Generation via AceDataCloud API. Runs locally from the mcp-midjourney Python package. Needs 1 environment variable to run.
alice
Alice: the continuity layer for AI agents. Local-first memory with provenance, open loops, resumption, and review-governed writes. Runs locally from the alice-memory Python package.