# Tugra (npm · tugra)

Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.

- Trust score: 87/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- npm · `tugra`: 87/100 (this document), [markdown](https://verifymcp.io/servers/com-tugra-ai-tugra/tugra.md), [page](https://verifymcp.io/servers/com-tugra-ai-tugra/tugra)

## Channel facts

- Registry: `npm`
- Package: `tugra`
- Version: `0.1.4`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 4 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to dogrucanemek-alt/tugra).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 415 tokens (~103/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 73/100
  - Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 79/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 38% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Tugra MCP server?

Tugra runs locally as an npm package, launched with npx -y tugra. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-tugra-ai-tugra -- npx -y tugra
```

### Cursor

```json
{
  "mcpServers": {
    "com-tugra-ai-tugra": {
      "command": "npx",
      "args": [
        "-y",
        "tugra"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-tugra-ai-tugra": {
      "command": "npx",
      "args": [
        "-y",
        "tugra"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-tugra-ai-tugra -- npx -y tugra
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-tugra-ai-tugra": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "tugra"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-tugra-ai-tugra --command npx --arg -y --arg tugra
```

### Hermes

```yaml
mcp_servers:
  com-tugra-ai-tugra:
    command: "npx"
    args: ["-y", "tugra"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-tugra-ai-tugra": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "tugra"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-tugra-ai-tugra -t stdio -c npx -a -y tugra
```

### Other

```json
{
  "mcpServers": {
    "com-tugra-ai-tugra": {
      "command": "npx",
      "args": [
        "-y",
        "tugra"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 83, +27)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 1.00

### 2026-09-10 (score 56, −26)

- [security regression] Known CVEs: pass → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: 1.00 → unverified
- [functional] Package version: 0.1.1 → 0.1.4
- [functional] Package version: 0.1.1 → 0.1.2

### 2026-09-09 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 81, +4)

- [functional improvement] Stability: unverified → 0.30

## MCP tools (4)

### `fact_search` (~132 tokens)

Search stored facts. Retired and rotten facts are omitted unless archive is true. Rank: token score, then freshness, then confidence. Boundary facts add a no-claim warning. Authorization required.

Input parameters:

- `agent` (string): authorization agent id (default mcp-readonly@tugra)
- `archive` (boolean): include retired and rotten facts; default is the active set
- `limit` (integer)
- `query` (string, required): search text
- `scope` (string): evrensel | kurum | dunya (stored scope values)
- `world` (string): world id when scope is dunya

### `fact_read` (~63 tokens)

Read one fact by uid. Body passes through the presentation layer (injection escaping). Retired facts include superseded_by and the reason.

Input parameters:

- `agent` (string): authorization agent id (default mcp-readonly@tugra)
- `uid` (string, required)

### `fact_propose` (~133 tokens)

Write a draft fact under kasa/_oneriler/ (or quarantine). Secret patterns are rejected before any write; the matching text is never returned. type=boundary is always quarantined. Fake mcp:// sources are not injected.

Input parameters:

- `agent` (string, required): authorization agent id
- `body` (string, required)
- `source` (array): real evidence; if omitted, kaynak is written empty — mcp:// is not injected
- `title` (string, required)
- `topic` (string)
- `type` (string): stored as tur; boundary is always quarantined
- `world` (string)

### `event_report` (~87 tokens)

Append a telemetry line to akis/YYYY-MM-DD.jsonl. No network.

Input parameters:

- `action` (string, required)
- `agent` (string, required)
- `blocked` (string|null)
- `confidence` (number)
- `job` (string, required)
- `note` (string)
- `status` (string, required)
- `touched` (array)
- `world` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-tugra-ai-tugra/tugra#diagnostics

## Score history

- 2026-09-21: 87
- 2026-09-20: 87
- 2026-09-19: 87
- 2026-09-18: 86
- 2026-09-17: 86
- 2026-09-16: 85
- 2026-09-15: 85
- 2026-09-14: 84
- 2026-09-13: 84
- 2026-09-12: 83
- 2026-09-11: 83
- 2026-09-10: 56
- 2026-09-09: 82
- 2026-09-08: 81
- 2026-09-07: 77
- 2026-09-06: 77
- 2026-09-05: 77
- 2026-09-04: 77
- 2026-09-03: 77
- 2026-09-02: 77
- 2026-09-01: 77
- 2026-08-31: 77
- 2026-08-30: 62

## Common questions

### What is the Tugra MCP server?

Tugra is an MCP server listed in the public MCP registry as com.tugra-ai/tugra. Provenance-aware memory format for AI agents: every claim carries its source, age and boundary. This page covers its npm package (tugra).

### Is the Tugra MCP server safe to use?

Tugra scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Tugra MCP server expose?

Tugra exposes 4 tools: fact_search, fact_read, fact_propose, event_report. Their descriptions and schemas cost roughly 415 tokens of context every time the server is loaded.

### Is the Tugra MCP server still maintained?

Tugra is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Tugra MCP server under?

Tugra declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/tugra
- Socket report: https://socket.dev/npm/package/tugra
- Repository: https://github.com/dogrucanemek-alt/tugra
- Website: https://tugra-ai.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-tugra-ai-tugra/tugra.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-tugra-ai-tugra/tugra.json
- HTML version of this page: https://verifymcp.io/servers/com-tugra-ai-tugra/tugra