content-validity-index-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | 127.0.0.1 | |
| MCP_PORT | No | 8000 | |
| MCP_API_KEY | No | API key untuk klien non-OAuth | |
| MCP_BASE_URL | No | URL publik untuk OAuth | |
| MCP_TRANSPORT | No | stdio | |
| BACKEND_API_TOKEN | No | Token Authentik untuk stdio | |
| AUTHENTIK_CLIENT_ID | No | Client ID OAuth | |
| AUTHENTIK_ISSUER_URL | No | Issuer OIDC | |
| BACKEND_API_BASE_URL | No | Base URL backend | http://localhost:8000 |
| AUTHENTIK_ADMIN_GROUP | No | cvi-admin | |
| AUTHENTIK_EXPERT_GROUP | No | cvi-expert | |
| AUTHENTIK_CLIENT_SECRET | No | Client Secret OAuth |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| whoamiA | Ambil profil user saat ini dan sinkronkan dari Authentik. Memanggil Returns:
Dict profil user ( |
| list_instrumentsA | Daftar instrumen penelitian yang dapat diakses user. Hasil difilter backend sesuai role: admin melihat semua instrumen, expert melihat instrumen yang ditugaskan kepadanya. |
| get_instrumentB | Ambil detail satu instrumen berdasarkan ID. |
| list_instrument_itemsB | Daftar item (butir) pada sebuah instrumen. |
| list_instrument_domainsB | Daftar dimensi/domain (beserta definisi konstruk) pada instrumen. Setiap domain menyertakan |
| create_instrument_domainB | Buat dimensi/domain baru pada sebuah instrumen (khusus admin). |
| update_instrument_domainA | Perbarui dimensi/domain pada instrumen (khusus admin). Hanya field yang diisi (non-null) yang dikirim ke backend; field yang dibiarkan kosong tidak diubah. Untuk mengosongkan sebuah field, gunakan antarmuka web (tool ini tidak mengirim nilai null eksplisit). |
| delete_instrument_domainA | Hapus dimensi/domain dari instrumen (khusus admin). Item yang terkait domain ini akan kehilangan referensi domain-nya
( |
| calculate_cviA | Hitung hasil Content Validity Index (CVI) sebuah instrumen. Mengembalikan I-CVI per item, S-CVI/Ave, S-CVI/UA, dan interpretasinya berdasarkan penilaian para expert. Memerlukan akses admin di backend. |
| list_my_assignmentsA | Daftar penugasan penilaian (assignment) milik user expert saat ini. Returns:
List penugasan expert, atau dict |
| list_assignment_ratingsB | Daftar penilaian (rating) pada sebuah penugasan. |
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 11 tools
Each tool has a clearly distinct purpose: domain CRUD, list instruments/domains/items/assignments/ratings, calculate CVI, get instrument, and whoami. No overlapping functionality.
Tool names consistently follow a verb_noun pattern in snake_case (e.g., create_instrument_domain, list_instruments). The only exception is 'whoami', which is a widely accepted idiom.
With 11 tools covering instruments, domains, items, assignments, ratings, user info, and CVI calculation, the count is well-scoped for the domain without being overwhelming or insufficient.
The set lacks CRUD for instruments and items (only get and list are provided). This creates notable gaps, as users cannot create or update these core entities via the MCP server.