obsify
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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_piiA | Scan a file or folder for PII and return TYPES + LOCATIONS + COUNTS only — never the detected values. Safe to surface to an LLM: it learns what PII exists and where, without the substance entering context. Recurses into subfolders; skips unreadable files and caps very large sheets, reporting both as notes.
|
| redact_textA | Return
|
| verify_value_freeA | Fail-closed check that |
| make_synthetic_twinA | Generate a SYNTHETIC TWIN of a real Excel workbook at |
| run_on_realA | COMPUTE-TO-DATA: execute your Python |
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 clear, distinct purpose: make_synthetic_twin creates a fake dataset, run_on_real executes code against real data, scan_pii identifies PII locations, redact_text masks PII in text, and verify_value_free checks for forbidden terms. No two tools overlap in what they accomplish.
Most tools follow a verb_noun pattern (make_synthetic_twin, scan_pii, redact_text, verify_value_free), but run_on_real breaks the pattern with a prepositional phrase. The style is consistent (all snake_case, verbs first) but the deviation is noticeable.
With 5 tools, the count is well-scoped for a focused PII-handling server. Each tool covers a necessary step in the workflow, and the count is within the typical 3-15 range, though a few additional helpers could be justified (e.g., a check for twin accuracy).
The tool surface covers the core lifecycle: protect data (scan, redact, verify) and enable safe analysis (twin, run on real). Minor gaps exist, such as no tool to validate the synthetic twin's fidelity against the real file, and verify_value_free lacks a positive counterpart, but agents can work around these.