OpenArchiver MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENARCHIVER_API_KEY | Yes | Required API key. | |
| OPENARCHIVER_API_URL | No | Optional instance base URL; defaults to https://archiver.alghul.com. | https://archiver.alghul.com |
| OPENARCHIVER_TOOLSET | No | core or full; defaults to core. Invalid values stop startup with an error. | core |
| OPENARCHIVER_TIMEOUT_MS | No | Positive request timeout in milliseconds; defaults to 30000. | 30000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_emailsB | Search archived emails with full-text search and structured filters |
| get_emailA | Get one archived email by ID, including attachments and thread details |
| get_archive_statsB | Get overall dashboard statistics and detailed statistics for one ingestion source |
| list_ingestion_sourcesA | List ingestion sources accessible to the current API key |
| list_archived_emails_for_sourceA | List archived emails for one ingestion source |
| get_archive_healthB | Get global index health and, optionally, source health; full mode also includes the admin search-engine overview |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a distinct purpose: get_email retrieves a single record, search_emails and list_archived_emails_for_source provide different listing/search paths, and the stats/health/source tools cover separate operational concerns. There is no meaningful overlap that would confuse an agent selecting a tool.
Tool names consistently follow a get_/list_/search_ verb prefixed pattern with clear noun targets. Longer names like list_archived_emails_for_source remain readable and predictable, and no naming style mixing occurs.
Six tools is a well-scoped count for an archive email server covering retrieval, search, source listing, and monitoring. Each tool earns its place without redundancy or bloat.
The read-only archive surface is well covered: emails can be searched, listed by source, and fetched individually, while stats and health provide operational visibility. There are no tools for managing ingestion sources or email lifecycle operations, but those appear outside the intended scope of an archiver query/monitoring server.