# TomeVault MCP server

Search, fetch (with provenance), scan, and convert AI instruction files for agents.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-olijboyd-tomevault

## Install
- Endpoint: https://mcp.tomevault.io/
- Auth: Not captured

## Setup notes
- Remote endpoint: https://mcp.tomevault.io/

## Tools
- search_tomes - Search TomeVault for agent context files (tomes, configs, skills) by a task description. Filter by format, kind, and quality grade. Returns ranked matches with owner/repo, grade, and available formats, not file contents. Endpoint: https://mcp.tomevault.io/
- get_tome - Fetch one tome's content in a specific agent format (default claude_md). Every response carries the provenance verdict: quality grade, security scan grade, decay risk, and the content hash it is bound to. Endpoint: https://mcp.tomevault.io/
- get_provenance - Return the signed attestation record alone for a tome: quality grade, security scan grade and flags, decay risk, source registry, the content hash it is bound to, and the signing key id for offline verification. Endpoint: https://mcp.tomevault.io/
- scan_content - Scan submitted instruction-file text for safety, clarity, loadability, and cross-model consistency, and return a verdict with findings. Use before loading a third-party file. Consistency findings are PREDICTIONS (divergence risks across models/tools), never verified facts. The submitted text is scanned and discarded, never stored. Endpoint: https://mcp.tomevault.io/
- convert_content - Convert pasted instruction-file text into another tool's format (claude_md, agents_md, cursor_mdc, gemini_md, copilot_instructions, windsurf_rules, skill_md). The same instructions, ready for any tool. Endpoint: https://mcp.tomevault.io/
- verify_attestation - Verify a TomeVault attestation document (the contents of a repo's .tome/attestation.json). Confirms the detached signature is genuinely TomeVault's against the published key, and, if the signed file's text is supplied, that the file has not drifted since it was signed. Returns the signed verdict; consistency in it is a PREDICTION (cross-model divergence risk), never a verified fact. Nothing submitted is stored. Endpoint: https://mcp.tomevault.io/
- list_vault_items - List the items in your TomeVault that this token can read. Requires a vault access token with the items:read scope. Encrypted (private) items are never listed. Endpoint: https://mcp.tomevault.io/
- get_vault_item - Fetch one of your TomeVault items by id, with its content. Requires a vault access token with the items:read scope. Encrypted items are not retrievable and return not found, indistinguishable from a missing id. Endpoint: https://mcp.tomevault.io/

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.olijboyd
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jun 15, 2026
- Source: https://registry.modelcontextprotocol.io