Eidolon
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Host URL for Ollama LLM service | http://localhost:11434 |
| HIBP_API_KEY | No | API key for Have I Been Pwned | |
| DEHASHED_API_KEY | No | API key for DeHashed |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_targetA | Start a privacy-OSINT scan. Returns immediately with a scan_id. The scan runs in the background and takes several minutes. Poll scan_status(scan_id) until it reports "done", then call get_report(scan_id). Only one scan runs at a time. Provide at least one of email / phone / name (name works best with a city/state). Leaked credentials are never in the headline result — use reveal_credentials(scan_id) for those. |
| scan_statusA | Check a scan started by scan_target: status is running | done | error. When done, includes the headline result (risk, summary, top risks, report paths) and which sources were skipped because no API token was configured. Then call get_report(scan_id). |
| list_scansA | List previously run scans (newest first): scan_id, identifier, date, paths. |
| get_reportA | Return a scan's report. The markdown is returned with the leaked-credentials section removed; call reveal_credentials(scan_id) to see those. |
| reveal_credentialsA | Return the leaked-credentials dossier for a scan (plaintext passwords). This is the explicit gate for the most sensitive output — only call it when the user has clearly asked to see the actual leaked credentials. |
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 5 tools
Each tool has a unique, clearly defined role: starting a scan, checking its status, listing past scans, retrieving reports, and revealing leaked credentials. No two tools overlap in purpose or output.
All tool names follow a consistent verb_noun pattern (scan_target, scan_status, list_scans, get_report, reveal_credentials), using lowercase with underscores throughout. The convention is uniform and predictable.
Five tools is well-scoped for a privacy OSINT server. Each tool covers a necessary step in the scanning workflow without redundancy or bloat, making the set feel complete and manageable.
The tool set covers the full scan lifecycle: initiate, monitor, list history, retrieve general report, and access sensitive credentials. There are no obvious dead ends, and the guidance in descriptions ensures agents can navigate the workflow seamlessly.