# KarmaDue (remote · karmadue--mcp.expo.app)

Pre-install safety check for agents: known traps, tested fixes, malware reports. No account.

- Trust score: 77/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-07

## Components

- remote · `ogogoizwsfaduzehkshb.supabase.co`: 63/100, [markdown](https://verifymcp.io/servers/ashadow07-karmadue/functions-v1-mcp.md), [page](https://verifymcp.io/servers/ashadow07-karmadue/functions-v1-mcp)
- remote · `ogogoizwsfaduzehkshb.supabase.co`: 77/100, [markdown](https://verifymcp.io/servers/ashadow07-karmadue/functions-v1-mcp-connector.md), [page](https://verifymcp.io/servers/ashadow07-karmadue/functions-v1-mcp-connector)
- remote · `karmadue--mcp.expo.app`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ashadow07-karmadue/karmadue-mcp.md), [page](https://verifymcp.io/servers/ashadow07-karmadue/karmadue-mcp)

## Channel facts

- Endpoint: `https://karmadue--mcp.expo.app/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-07.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 843 tokens (~168/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 24 days we've observed: 27 tool removals, 0 breaking changes, 0 auth/transport breaks, 3 additions.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% 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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

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

KarmaDue is a hosted endpoint at https://karmadue--mcp.expo.app/mcp, so there is nothing to install locally. 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 --transport http ashadow07-karmadue 'https://karmadue--mcp.expo.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ashadow07-karmadue": {
      "url": "https://karmadue--mcp.expo.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ashadow07-karmadue": {
      "type": "http",
      "url": "https://karmadue--mcp.expo.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ashadow07-karmadue]
url = "https://karmadue--mcp.expo.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ashadow07-karmadue": {
      "type": "remote",
      "url": "https://karmadue--mcp.expo.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ashadow07-karmadue --url 'https://karmadue--mcp.expo.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ashadow07-karmadue:
    url: "https://karmadue--mcp.expo.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ashadow07-karmadue": {
      "Transport": "http",
      "Url": "https://karmadue--mcp.expo.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ashadow07-karmadue -t streamable-http -u 'https://karmadue--mcp.expo.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ashadow07-karmadue": {
      "type": "http",
      "url": "https://karmadue--mcp.expo.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-06 (score 77, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-10-19 (score 77, 0)

- [cosmetic] “check_install” added an optional parameter “detail”

### 2026-10-18 (score 77, 0)

- [security] Tool “check_install” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 42% → 85%
- [cosmetic] “check_install” added an optional parameter “request_repro”
- [cosmetic] “report_leaf” reworded the description of “runtime_env”
- [cosmetic] “report_leaf” reworded the description of “stderr_snippet”
- [cosmetic] “report_leaf” reworded the description of “target”
- [cosmetic] “check_install” reworded the description of “ecosystem”
- [cosmetic] “report_leaf” reworded the description of “command_run”
- [cosmetic] “report_leaf” reworded the description of “status”

### 2026-10-15 (score 77, −2)

- [security regression] Stability: unverified → fail
- [security regression] A breaking change shipped without a version bump: still 1.1.0
- [security regression] Tool “check_before_acting” was removed
- [security regression] Tool “check_manifest” was removed
- [security regression] Tool “discover_resources” was removed
- [security regression] Tool “find_collaborators” was removed
- [security regression] Tool “get_challenge” was removed
- [security regression] Tool “get_claims” was removed
- [security regression] Tool “get_credits” was removed
- [security regression] Tool “get_history” was removed
- [security regression] Tool “get_ladder” was removed
- [security regression] Tool “get_rating_card” was removed
- [security regression] Tool “get_receipt” was removed
- [security regression] Tool “get_resource” was removed
- [security regression] Tool “get_standing” was removed
- [security regression] Tool “get_thread” was removed
- [security regression] Tool “get_watchlist” was removed
- [security regression] Tool “list_challenges” was removed
- [security regression] Tool “list_threads” was removed
- [security regression] Tool “list_topics” was removed
- [security regression] Tool “lookup_findings” was removed
- [security regression] Tool “notify_human_of_finding” was removed
- [security regression] Tool “read_scores” was removed
- [security regression] Tool “read_stream” was removed
- [security regression] Tool “withdraw_finding” was removed
- [security regression] Tool “watchlist_changes” was removed
- [security regression] Tool “verify_agent” was removed
- [security regression] Tool “trust_query” was removed
- [security regression] Tool “set_watchlist” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “search” rewrote its description, which is the text the model reads
- [security] Tool “fetch” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 100% → 42%
- [functional improvement] Schema quality: fail → pass
- [functional] Destructive annotations: 100 → pass
- [functional] New tool “search_recipes”
- [functional] New tool “report_leaf”
- [functional] New tool “check_install”
- [cosmetic] “fetch” reworded the description of “id”
- [cosmetic] “search” reworded the description of “query”
- [cosmetic] “search” dropped the optional parameter “offset”
- [cosmetic] “search” dropped the optional parameter “include_examples”
- [cosmetic] “search” dropped the optional parameter “category”

### 2026-10-14 (score 79, +40)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 100
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-10-12 (score 39)

First indexed and scored.

## MCP tools (5)

### `check_install` (~376 tokens)

Read-only. Call before npm/pnpm/yarn install, pip install, uv add, npx or uvx, or adding an MCP server, including setup commands from a README or tutorial. Returns v, enforce, why; on known traps fix (tested steps), do_not (what failed, where), test, source. enforce=block: stop. enforce=ask: ask your person first. v=fix_first: use fix, not your command. Also returns safety (OSV advisories and malicious-package reports: verdict, advisories, fixed_in). When no tested record exists, repro_request says how to queue one with request_repro 'yes' (the only case where this call records anything: one anonymous request). Missing evidence is not safety clearance. Skip packages already pinned in a lockfile you are not changing.

Input parameters:

- `detail` (string): Optional. 'full' adds tested_on, untruncated notes, records and links.
- `ecosystem` (string, required): Package ecosystem of the target: npm (npm, pnpm, yarn, npx), pypi (pip, uv, uvx) or mcp (an MCP server you are about to add, or a bare name that may exist in more than one ecosystem). A bare name fou…
- `request_repro` (string): Optional. 'yes' queues one anonymous reproduction request (package and version only) when no tested record exists for the target.
- `runtime_env` (string): Optional, e.g. node 20 linux.
- `target` (string, required): Package or server as you would install it, e.g. tailwindcss@4, psycopg2, @modelcontextprotocol/server-filesystem.

### `search_recipes` (~72 tokens)

Call when an install, build or import fails, before retrying or guessing a fix. Paste the key error line; returns tested fixes.

Input parameters:

- `error_signature` (string, required): The key error line, verbatim.
- `runtime_env` (string): Optional, e.g. python 3.13 macos.

### `report_leaf` (~181 tokens)

Only if your owner opted in: after an install finishes, report pass or fail and the command. Reviewed before use.

Input parameters:

- `command_run` (string, required): The exact install command you ran, e.g. npm i -D tailwindcss@4. No secrets or tokens.
- `runtime_env` (string, required): Your setup, e.g. node 20 linux or python 3.13 macos.
- `status` (string, required): Outcome of the install: pass if it finished and worked, fail if it errored.
- `stderr_snippet` (string): Optional. The key error lines if it failed, verbatim. Never include secrets, tokens or personal data.
- `target` (string, required): Package or server you installed, as you passed it to check_install, e.g. tailwindcss@4 or @modelcontextprotocol/server-filesystem.

### `search` (~26 tokens)

Search PinTree records for packages, tools and MCP servers.

Input parameters:

- `query` (string, required)

### `fetch` (~22 tokens)

Fetch one record by id from search.

Input parameters:

- `id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ashadow07-karmadue/karmadue-mcp#diagnostics

## Score history

- 2026-11-07: 77
- 2026-11-06: 77
- 2026-11-05: 77
- 2026-11-04: 77
- 2026-11-03: 77
- 2026-11-02: 77
- 2026-11-01: 77
- 2026-10-31: 77
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 77
- 2026-10-27: 77
- 2026-10-26: 77
- 2026-10-25: 77
- 2026-10-24: 77
- 2026-10-23: 77
- 2026-10-22: 77
- 2026-10-21: 77
- 2026-10-20: 77
- 2026-10-19: 77
- 2026-10-18: 77
- 2026-10-17: 77
- 2026-10-16: 77
- 2026-10-15: 77
- 2026-10-14: 79
- 2026-10-13: 39
- 2026-10-12: 39

## Common questions

### What is the KarmaDue MCP server?

KarmaDue is an MCP server listed in the public MCP registry as io.github.ashadow07/karmadue. Pre-install safety check for agents: known traps, tested fixes, malware reports. No account. This page covers its hosted endpoint (https://karmadue--mcp.expo.app/mcp).

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

KarmaDue scores 77 out of 100 on VerifyMCP. 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 KarmaDue MCP server expose?

KarmaDue exposes 5 tools: check_install, search_recipes, report_leaf, search, fetch. Their descriptions and schemas cost roughly 677 tokens of context every time the server is loaded.

### Does the KarmaDue MCP server require authentication?

Yes. KarmaDue asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the KarmaDue MCP server still maintained?

KarmaDue is still listed as active in the MCP registry. We last reached this channel on 7 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the KarmaDue MCP server?

VerifyMCP ran 13 checks on KarmaDue, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://karmadue--mcp.expo.app/mcp
- Repository: https://github.com/ashadow07/karmadue
- Website: https://karmadue.expo.app/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ashadow07-karmadue/karmadue-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ashadow07-karmadue/karmadue-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ashadow07-karmadue/karmadue-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ashadow07-karmadue/karmadue-mcp