A side-by-side look at the Gramps Evidence and PDF Reader MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Gramps Evidence for developer tools work as a local process; choose PDF Reader MCP for search & data extraction. You can also run both side by side in one mcpServers block.
GRAMPS_MCP_API_URL, GRAMPS_MCP_USERNAME, GRAMPS_MCP_PASSWORD.add_person, add_family, add_event_to_person.inspect, outline, read.Rows where the two servers differ are marked.
| Spec | G Gramps Evidence | |
|---|---|---|
| Category | Developer Tools | Search & Data Extraction |
| Quality signal | 53/100 · Good | 65/100 · Great |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | other | No auth required |
| Pricing | Free | Free |
| Required env vars | GRAMPS_MCP_API_URLGRAMPS_MCP_USERNAMEGRAMPS_MCP_PASSWORD | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 1,041 |
| Directory activity | 0 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 80 | 4 |
| Full listing | View Gramps Evidence | View PDF Reader MCP |
add_personCreate a person, optionally with cited birth/death events; each event's type may be left out.add_familyLink parents + children with an optional cited marriage. A child may be given with its relationship to each parent — a stepchild in the same call.add_event_to_personAdd a cited event (residence, census, occupation…) to a person.add_event_to_familyAdd a dated/placed event (marriage, divorce…) to a family.add_child_to_familyAdd an existing person as a child of an existing family.add_event_refShare an **existing** event with another person, in a role (Witness, Informant, Godparent…): one census entry or burial, one set of citations. What is the person's own — their line on the sheet, their age — goes on the reference as attributes (`As enumerated`, `Age`).add_alternate_nameAdd a non-primary name (AKA, married name, nickname) to a person, with the citation for that form of the name.add_sourceCreate a Source (record set, book, certificate), optionally in a repository.add_citationCreate/reuse a standalone Citation on a Source.add_repositoryCreate a Repository (archive, library, cemetery, website).add_placeCreate a place deliberately, typed and parented, instead of letting one appear as a side effect of naming it in an event.add_noteCreate a note, optionally attached to an object. Re-reads the target and returns `verified: false` rather than claiming an attachment it can't demonstrate. Any length in one call; a server error says whether anything was written, and an attach that failed takes the new note back.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".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.
{
"mcpServers": {
"gramps-evidence": {
"command": "uvx",
"args": [
"gramps-evidence-mcp"
],
"env": {
"GRAMPS_MCP_API_URL": "YOUR_GRAMPS_MCP_API_URL_HERE",
"GRAMPS_MCP_USERNAME": "YOUR_GRAMPS_MCP_USERNAME_HERE",
"GRAMPS_MCP_PASSWORD": "YOUR_GRAMPS_MCP_PASSWORD_HERE"
}
}
}
}
No confirmed install command for PDF Reader MCP yet — follow the setup steps linked from its listing page rather than a guessed package name.