# io.github.CloudCorpRecords/embedbase (oci · ghcr.io/cloudcorprecords/embedbase)

Vector collections and document search backed by a Chroma HTTP service.

- Trust score: 41/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@reneturcios/embedbase`: 63/100, [markdown](https://verifymcp.io/servers/cloudcorprecords-embedbase/reneturcios-embedbase.md), [page](https://verifymcp.io/servers/cloudcorprecords-embedbase/reneturcios-embedbase)
- oci · `ghcr.io/cloudcorprecords/embedbase`: 41/100 (this document), [markdown](https://verifymcp.io/servers/cloudcorprecords-embedbase/ghcr-io-cloudcorprecords-embedbase.md), [page](https://verifymcp.io/servers/cloudcorprecords-embedbase/ghcr-io-cloudcorprecords-embedbase)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/cloudcorprecords/embedbase`
- Version: `0.1.0`
- 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 2026-11-05.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 836 tokens (~69/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "chroma_delete_collection" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 12 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.CloudCorpRecords/embedbase MCP server?

io.github.CloudCorpRecords/embedbase runs locally as a container image, launched with docker run --rm -i ghcr.io/cloudcorprecords/embedbase:0.1.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add cloudcorprecords-embedbase -- docker run --rm -i ghcr.io/cloudcorprecords/embedbase:0.1.0
```

### Cursor

```json
{
  "mcpServers": {
    "cloudcorprecords-embedbase": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/cloudcorprecords/embedbase:0.1.0"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cloudcorprecords-embedbase": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/cloudcorprecords/embedbase:0.1.0"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cloudcorprecords-embedbase -- docker run --rm -i ghcr.io/cloudcorprecords/embedbase:0.1.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cloudcorprecords-embedbase": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/cloudcorprecords/embedbase:0.1.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  cloudcorprecords-embedbase:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/cloudcorprecords/embedbase:0.1.0"]
```

### Netclaw

```json
{
  "McpServers": {
    "cloudcorprecords-embedbase": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/cloudcorprecords/embedbase:0.1.0"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "cloudcorprecords-embedbase": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/cloudcorprecords/embedbase:0.1.0"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 41, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 40, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 39, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 38)

First indexed and scored.

## MCP tools (12)

### `chroma_list_collections` (~48 tokens)

List collections in the database with optional pagination.

Input parameters:

- `limit` (integer): Maximum number of collections to return.
- `offset` (integer): Number of collections to skip before returning results.

### `chroma_create_collection` (~67 tokens)

Create a new collection with optional metadata and embedding function.

Input parameters:

- `collection_name` (string, required): Name of the collection to create.
- `embedding_function_name` (string): Name of the embedding function to use for the collection.
- `metadata` (object): Metadata to associate with the collection.

### `chroma_peek_collection` (~48 tokens)

Return a preview of documents stored in a collection.

Input parameters:

- `collection_name` (string, required): Name of the collection to preview.
- `limit` (integer): Maximum number of documents to preview.

### `chroma_get_collection_info` (~36 tokens)

Get metadata and configuration details for a collection.

Input parameters:

- `collection_name` (string, required): Name of the collection to get information for.

### `chroma_get_collection_count` (~37 tokens)

Get the number of records stored in a collection.

Input parameters:

- `collection_name` (string, required): Name of the collection to count records in.

### `chroma_modify_collection` (~62 tokens)

Rename a collection or replace its metadata.

Input parameters:

- `collection_name` (string, required): Name of the collection to modify.
- `new_metadata` (object): New metadata to replace the collection's existing metadata.
- `new_name` (string): New name for the collection.

### `chroma_delete_collection` (~33 tokens)

Delete a collection and all of its records.

Input parameters:

- `collection_name` (string, required): Name of the collection to delete.

### `chroma_add_documents` (~93 tokens)

Add documents with optional metadata and ids to a collection.

Input parameters:

- `collection_name` (string, required): Name of the collection to add documents to.
- `documents` (array, required): Document texts to add to the collection.
- `ids` (array): Ids for the documents, aligned by position with documents; generated when omitted.
- `metadatas` (array): Metadata objects for each document, aligned by position with documents.

### `chroma_query_documents` (~127 tokens)

Query a collection for documents nearest to the given query texts.

Input parameters:

- `collection_name` (string, required): Name of the collection to query.
- `include` (array): Fields to include in the results, such as documents, metadatas, embeddings, or distances.
- `n_results` (integer): Maximum number of results to return for each query text.
- `query_texts` (array, required): Query texts to find the nearest documents for.
- `where` (object): Metadata filter to apply to the query.
- `where_document` (object): Document-content filter to apply to the query.

### `chroma_get_documents` (~116 tokens)

Retrieve documents from a collection by ids or filter.

Input parameters:

- `collection_name` (string, required): Name of the collection to retrieve documents from.
- `ids` (array): Ids of the documents to retrieve.
- `include` (array): Fields to include in the results, such as documents, metadatas, or embeddings.
- `limit` (integer): Maximum number of documents to return.
- `offset` (integer): Number of documents to skip before returning results.
- `where` (object): Metadata filter selecting which documents to retrieve.

### `chroma_update_documents` (~105 tokens)

Update documents, metadata, or embeddings for existing ids in a collection.

Input parameters:

- `collection_name` (string, required): Name of the collection containing the documents to update.
- `documents` (array): Replacement document texts, aligned by position with ids.
- `embeddings` (array): Replacement embedding vectors, aligned by position with ids.
- `ids` (array, required): Ids of the documents to update.
- `metadatas` (array): Replacement metadata objects, aligned by position with ids.

### `chroma_delete_documents` (~64 tokens)

Delete documents from a collection by ids or filter.

Input parameters:

- `collection_name` (string, required): Name of the collection to delete documents from.
- `ids` (array): Ids of the documents to delete.
- `where` (object): Metadata filter selecting which documents to delete.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/cloudcorprecords-embedbase/ghcr-io-cloudcorprecords-embedbase#diagnostics

## Score history

- 2026-11-05: 41
- 2026-11-04: 41
- 2026-11-03: 40
- 2026-11-02: 40
- 2026-11-01: 39
- 2026-10-31: 39
- 2026-10-30: 38

## Common questions

### What is the io.github.CloudCorpRecords/embedbase MCP server?

io.github.CloudCorpRecords/embedbase is an MCP server listed in the public MCP registry as io.github.CloudCorpRecords/embedbase. Vector collections and document search backed by a Chroma HTTP service. This page covers its container image (ghcr.io/cloudcorprecords/embedbase).

### Is the io.github.CloudCorpRecords/embedbase MCP server safe to use?

io.github.CloudCorpRecords/embedbase scores 41 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 io.github.CloudCorpRecords/embedbase MCP server expose?

io.github.CloudCorpRecords/embedbase exposes 12 tools: chroma_list_collections, chroma_create_collection, chroma_peek_collection, chroma_get_collection_info, chroma_get_collection_count, and 7 more. Their descriptions and schemas cost roughly 836 tokens of context every time the server is loaded.

### Is the io.github.CloudCorpRecords/embedbase MCP server still maintained?

io.github.CloudCorpRecords/embedbase is still listed as active in the MCP registry. We last reached this channel on 5 November 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 io.github.CloudCorpRecords/embedbase MCP server under?

io.github.CloudCorpRecords/embedbase declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/cloudcorprecords/embedbase
- Repository: https://github.com/CloudCorpRecords/embedbase
- Changelog RSS feed: https://verifymcp.io/servers/cloudcorprecords-embedbase/ghcr-io-cloudcorprecords-embedbase.xml
- Changelog JSON feed: https://verifymcp.io/servers/cloudcorprecords-embedbase/ghcr-io-cloudcorprecords-embedbase.json
- HTML version of this page: https://verifymcp.io/servers/cloudcorprecords-embedbase/ghcr-io-cloudcorprecords-embedbase