Privi Network
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.
Read-only catalog of six distinct, remote Privi MCP servers. The catalog is not an execution proxy and never bypasses paid-service access. Use each service's current MCP endpoint under that service's own payment and authentication terms.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| privi_network_service_directoryA | Find current Privi Ledger, Verify, Anchor, Quantum, Call or Agent Survival MCP endpoints and their Glama listings. This is informational discovery only; the tool does not invoke, pay for, or grant access to commercial services. |
| privi_network_access_informationA | Show Privi's published human-review pricing and limitations on paid API access. No checkout, API credential, entitlement, or external paid action is created. |
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 2 tools
Both tools are purely informational surfaces about the Privi network, so an agent may hesitate over which to call when asked a general 'what is Privi' question. The descriptions do differentiate them (endpoint discovery vs. pricing/limitations), but the boundary is narrow and partly overlapping since pricing is arguably part of the service directory.
Both tools use a consistent privi_network_<noun_phrase> pattern with snake_case throughout, so the set is predictable. The deviation is minor: neither uses a verb, so the names describe resources rather than actions, which is acceptable but slightly less informative.
Two tools is thin even for a deliberately read-only informational server; the scope could reasonably justify a small handful more (e.g. per-service detail or status lookups). It is not a mismatch, but it sits at the borderline of under-scoped.
For the stated informational-only purpose, the surface covers discovery and pricing, which are the two most obvious needs. However, there is no tool to retrieve details for a single endpoint, check live availability/health, or fetch machine-readable pricing per service, leaving agents with dead ends beyond the two summary calls.