# TomeVault (remote · mcp.tomevault.io)

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

- Trust score: 66/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.tomevault.io`: 66/100 (this document), [markdown](https://verifymcp.io/servers/olijboyd-tomevault/mcp.md), [page](https://verifymcp.io/servers/olijboyd-tomevault/mcp)

## Channel facts

- Endpoint: `https://mcp.tomevault.io/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 849 tokens (~106/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 91% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http olijboyd-tomevault https://mcp.tomevault.io/
```

### Codex

```toml
[mcp_servers.olijboyd-tomevault]
url = "https://mcp.tomevault.io/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "olijboyd-tomevault": {
      "type": "remote",
      "url": "https://mcp.tomevault.io/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add olijboyd-tomevault --url https://mcp.tomevault.io/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  olijboyd-tomevault:
    url: "https://mcp.tomevault.io/"
```

### Other

```json
{
  "mcpServers": {
    "olijboyd-tomevault": {
      "type": "http",
      "url": "https://mcp.tomevault.io/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 64, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 64, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 62, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 61)

First indexed and scored.

## MCP tools (8)

### `search_tomes` (~139 tokens)

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.

Input parameters:

- `format` (string): Target tool format, e.g. claude_md, agents_md, cursor_mdc.
- `grade` (string): Screen by graded quality tier.
- `kind` (string): tome = full project config + skills; config = one config file; skill = one skill.
- `limit` (integer)
- `query` (string, required): Free-text task or topic to match.

### `get_tome` (~130 tokens)

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.

Input parameters:

- `format` (string): Output format, e.g. claude_md, agents_md, skill_md.
- `owner` (string, required): GitHub owner or org.
- `repo` (string, required): GitHub repository name.
- `skill_path` (string): Fetch a specific skill within the repo (the skill_path from a search_tomes result). Omit for the repo's primary unit.

### `get_provenance` (~97 tokens)

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.

Input parameters:

- `owner` (string, required): GitHub owner or org.
- `repo` (string, required): GitHub repository name.
- `skill_path` (string): Address a specific skill within the repo, e.g. skills/foo.

### `scan_content` (~104 tokens)

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.

Input parameters:

- `name` (string): Optional display name, e.g. CLAUDE.md.
- `text` (string, required): Raw instruction-file text to scan.

### `convert_content` (~113 tokens)

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.

Input parameters:

- `content` (string, required): The raw instruction-file text to convert.
- `description` (string): Optional one-line description for the converted file.
- `name` (string): Optional title for the converted file's heading/frontmatter.
- `to_format` (string, required): The target tool format.

### `verify_attestation` (~141 tokens)

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.

Input parameters:

- `attestation` (string, required): The .tome/attestation.json document text.
- `content` (string): Optional: the instruction file the attestation signs, to also confirm it has not changed.

### `list_vault_items` (~52 tokens)

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.

Input parameters:

- `limit` (integer)

### `get_vault_item` (~73 tokens)

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.

Input parameters:

- `id` (string, required): The vault item id, from list_vault_items.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/olijboyd-tomevault/mcp#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 65
- 2026-08-01: 65
- 2026-07-31: 64
- 2026-07-30: 64
- 2026-07-29: 63
- 2026-07-28: 63
- 2026-07-27: 62
- 2026-07-26: 61

## Links

- Remote endpoint: https://mcp.tomevault.io/
- Changelog RSS feed: https://verifymcp.io/servers/olijboyd-tomevault/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/olijboyd-tomevault/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/olijboyd-tomevault/mcp