# Kevros — Agentic Identity Trust

> Agentic identity trust: precision decisioning, cryptographic release tokens, hash-chained proof

- name: io.github.ndl-systems/kevros
- version: 0.3.6
- connection class: R0 (autonomous)
- trust: 83/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.ndl-systems%2Fkevros
- tools: https://api.protogrid.dev/v1/servers/io.github.ndl-systems%2Fkevros/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "kevros": {
      "type": "http",
      "url": "https://governance.taskhawktech.com/mcp/"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 45
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% -stale-237d
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 9 of 9 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,046 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 9, about 2,046 tokens to load them all
- tool set hash: 5d1af6766aae185ce99bccbe4e1f9cff
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.ndl-systems/kevros.svg)](https://protogrid.dev/servers/io.github.ndl-systems/kevros)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://governance.taskhawktech.com/mcp/ (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (9)

- `attest`: Create a hash-chained provenance record for an action you've taken. Each attestation extends the append-only evidence chain. The hash can be independently verified by any third party. Cost: $0.02 per call.
- `bind`: Declare an intent and cryptographically bind it to a command. Proves that the command was issued in service of the declared intent. Use verify-outcome after execution to close the loop. Cost: $0.02 per call.
- `bundle`: Generate a certifier-grade compliance evidence bundle. Contains hash-chained provenance, intent bindings, PQC attestations, and verification instructions. Independently verifiable without Kevros access. Cost: $0.05 per call.
- `check-peer`: Check another agent's trust score and governance history. Returns trust score (0-100), chain length, attestation count, and tier. Free, no API key needed.
- `health`: Check the governance gateway health status. Free.
- `status`: Check your current usage and quota: calls used, calls remaining, tier, rate limits, and billing status. Free.
- `verify`: Verify an action against policy bounds before executing it. Returns ALLOW (proceed), CONSTRAIN (proceed with modified values; emitted on the wire as the legacy value CLAMP - both refer to the same verdict, CONSTRAIN is the public name), or DENY (stop). Every verification is recorded in a hash-chained provenance ledger. Cost: $0.01 per call.
- `verify-outcome`: Verify that an executed action achieved its declared intent. Closes the loop: intent -> command -> action -> outcome -> verification. Free (included with bind).
- `verify-token`: Verify a release token from another agent. Confirms the token is authentic, was issued by the Kevros gateway, and remains currently authorized after any halt or mode transition. Free, no API key needed.