Image Reader MCP vs MCP Arr
A side-by-side look at the Image Reader MCP and MCP Arr MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Image Reader MCP for multimedia process work as a local process; choose MCP Arr for multimedia process as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Image Reader MCP when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
inspect, outline, read.
Choose MCP Arr when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You want tools like
arr_status, search, fetch.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Multimedia Process | Multimedia Process |
| Quality signal | 47/100 · Fair | 69/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | API key required |
| Pricing | Free | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 2 | 232 |
| Directory activity | 7 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 4 | 11 |
| Full listing | View Image Reader MCP | View MCP Arr |
Tools & capabilities
Image Reader MCP tools 4
inspectDocument and media evidence when Markdown is not enough. video_timeline (bounded scene/cue timeline) and render_frame (actual decoded frames), and cite_check (quote/location support, not semantic truth), are anymd Pro; PDF operations: inspect (page facts, metadata), render_page (PNG images), extract_regions (crop bounding boxes), ocr_pages / analyze_regions (configured OCR or vision provider), structure (JSON with document map, elements, geometry; profile quality|research adds trust and accessibility reports), compare (page-level diff of sources[0] vs sources[1]).outlineReturn a document heading tree with stable node ids, title paths, page/slide/chapter ranges and Markdown byte ranges. PDF bookmarks or detected headings, Word headings, PowerPoint slides, EPUB chapters and headings, HTML and Markdown. format json (default) or tree. Pass a node id to read to fetch that section.readRead any document as clean Markdown: PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX/XLS/ODS), CSV, EPUB, HTML or a web URL, Markdown/text, images (metadata + OCR), audio/video (metadata, chapters, subtitles). Pages/slides/sheets carry <!-- page N --> style markers for citation. Long documents stop at max_tokens (default 20000) and end with a cursor to continue; choose pages with pages: "1-5,8". A directory returns its readable files.searchSearch documents for text: one file, many files, whole directories (recursive, .gitignore aware), or URLs, across every format read supports. Returns each hit as file + page/slide/sheet + a snippet with the match in bold. mode auto (default) finds the exact phrase and falls back to BM25-ranked passages when there is none; literal or ranked force one. Narrow directories with glob, e.g. "*.pdf".
MCP Arr tools 11
arr_statusGet status of all supported *arr services. No local *arr services are currently configured, but TRaSH reference tools remain available.searchSearch across configured *arr libraries plus TRaSH Guides reference profiles. This is the primary discovery tool for remote MCP clients such as ChatGPT.fetchFetch a specific item returned by search. Accepts an opaque item id from the search tool.arr_search_allSearch across all configured *arr services for any mediatrash_list_profilesList available TRaSH Guides quality profiles for Radarr or Sonarr. Shows recommended profiles for different use cases (1080p, 4K, Remux, etc.)trash_get_profileGet a specific TRaSH Guides quality profile with all custom format scores, quality settings, and implementation detailstrash_list_custom_formatsList available TRaSH Guides custom formats. Can filter by category: hdr, audio, resolution, source, streaming, anime, unwanted, release, languagetrash_get_namingGet TRaSH Guides recommended naming conventions for your media server (Plex, Emby, Jellyfin, or standard)trash_get_quality_sizesGet TRaSH Guides recommended min/max/preferred sizes for each quality leveltrash_compare_profileCompare your quality profile against TRaSH Guides recommendations. Shows missing custom formats, scoring differences, and quality settings. Requires the corresponding *arr service to be configured.trash_compare_namingCompare your naming configuration against TRaSH Guides recommendations. Requires the corresponding *arr service to be configured.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Image Reader MCP
{
"mcpServers": {
"image-reader-mcp": {
"command": "npx",
"args": [
"-y",
"@sylphx/anymd"
]
}
}
}
MCP Arr
{
"mcpServers": {
"mcp-arr": {
"command": "npx",
"args": [
"-y",
"mcp-arr-server"
]
}
}
}
Frequently asked questions
Image Reader MCP is categorized under Multimedia Process and uses a local stdio subprocess. MCP Arr belongs to Multimedia Process and uses a local stdio subprocess. Pick Image Reader MCP for multimedia process work and MCP Arr for multimedia process.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Image Reader MCP is listed as free. Auth: no auth required. MCP Arr is listed as free. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add image-reader-mcp and mcp-arr as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Image Reader MCP has a quality signal of 47/100 (Fair) with 7 views, 0 installs and 2 GitHub stars. MCP Arr has 69/100 (Great) with 3 views, 0 installs and 232 GitHub stars.