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.
npx agentmods add instructions/groupdocs-viewer/groupdocs.viewer.mcp/agents-mdgit clone --depth 1 https://github.com/groupdocs-viewer/GroupDocs.Viewer.McpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01374 | $0.01374 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
GroupDocs.Viewer.Mcp AGENTS.md 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guide for AI coding agents
Brief orientation for AI coding agents (Claude Code, Copilot, Cursor, Aider, Amp, Codex) working in this repository.
What this repo is
A standalone MCP server for GroupDocs.Viewer for .NET — exposes document rendering and view-info inspection as AI-callable tools via the Model Context Protocol.
Published to NuGet as GroupDocs.Viewer.Mcp with the McpServer package type, and to ghcr.io/groupdocs-viewer/viewer-net-mcp + docker.io/groupdocs/viewer-net-mcp as a container image.
MCP tools exposed
| Tool | Description |
|---|---|
RenderPage |
Render a single document page as a PNG image. Returns a CallToolResult with both a TextContentBlock (saved file path: <source-stem>_page<N>.png) and an ImageContentBlock (PNG bytes inline as image/png). Supports PDF, Word, Excel, PowerPoint, ODT, RTF, HTML, and 170+ more formats; takes optional page (1-based, default 1) and password. |
GetViewInfo |
Return file type, page count, and per-page dimensions as JSON. No rendering performed. Optional password for protected documents. |
RenderPage is the only tool in the GroupDocs MCP family that returns a CallToolResult directly (rather than Task<string>) — it embeds the rendered image inline as an ImageContentBlock so AI clients can display the page without a separate fetch.
Folder layout
src/ ← all projects + sln + Directory.Build.props
GroupDocs.Viewer.Mcp/
Program.cs ← host bootstrap + stdio transport
ViewerLicenseManager.cs ← applies GroupDocs.Total license
Tools/
RenderPageTool.cs ← [McpServerTool] — RenderPage (returns CallToolResult)
GetViewInfoTool.cs ← [McpServerTool] — GetViewInfo (returns JSON string)
.mcp/
server.json ← NuGet.org reads this to generate mcp.json snippet
GroupDocs.Viewer.Mcp.csproj ← PackageType=McpServer + ToolCommandName
GroupDocs.Viewer.Mcp.Tests/
GroupDocs.Viewer.Mcp.sln
Directory.Build.props
build/
dependencies.props ← single source of truth for all versions
changelog/ ← one MD file per change (see changelog/README.md)
docker/
Dockerfile ← multi-stage, runtime on aspnet:10.0
docker-compose.yml
.github/workflows/ ← build_packages.yml, run_tests.yml, publish_prod.yml, publish_docker.yml
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.
- yesterday First seen · 100 lines · 1,374 tokens per session scan A ac67df7735ba
GroupDocs.Viewer.Mcp AGENTS.md is an instructions file published in the GitHub repository groupdocs-viewer/GroupDocs.Viewer.Mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,374 tokens to every session, about $0.0069 per session on Opus 5. 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 instructions, from other repositories
GroupDocs.Metadata.Mcp AGENTS.md
AGENTS.md instructions for groupdocs-metadata/GroupDocs.Metadata.Mcp, covering agents.md — guide for ai coding agents, what this repo is, mcp tools exposed, folder layout and dependencies.
GroupDocs.Signature.Mcp AGENTS.md
AGENTS.md instructions for groupdocs-signature/GroupDocs.Signature.Mcp, covering agents.md — guide for ai coding agents, what this repo is, mcp tools exposed, folder layout and dependencies.
GroupDocs.Parser.Mcp AGENTS.md
AGENTS.md instructions for groupdocs-parser/GroupDocs.Parser.Mcp, covering agents.md — guide for ai coding agents, what this repo is, mcp tools exposed, folder layout and dependencies.
GroupDocs.Redaction.Mcp AGENTS.md
AGENTS.md instructions for groupdocs-redaction/GroupDocs.Redaction.Mcp, covering agents.md — guide for ai coding agents, what this repo is, mcp tools exposed, folder layout and dependencies.
GroupDocs.Watermark.Mcp AGENTS.md
AGENTS.md instructions for groupdocs-watermark/GroupDocs.Watermark.Mcp, covering agents.md — guide for ai coding agents, what this repo is, mcp tools exposed, folder layout and dependencies.
GroupDocs.Comparison.Mcp AGENTS.md
AGENTS.md instructions for groupdocs-comparison/GroupDocs.Comparison.Mcp, covering agents.md — guide for ai coding agents, what this repo is, mcp tools exposed, folder layout and dependencies.