com.mcparmory/pinecone
OCI · GHCR.IO/MCPARMORY/PINECONE:1.0.2 · 2 COMPONENTS · SCANNED SEP 20
Create and manage vector database indexes, backups, and collections
Available components
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. How we score → Why this is hard to score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 130 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability72
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2873 tokens (~159/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
How do I install the com.mcparmory/pinecone MCP server?
com.mcparmory/pinecone runs locally as a container image, launched with docker run --rm -i ghcr.io/mcparmory/pinecone:1.0.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/mcparmory/pinecone:1.0.2
claude mcp add com-mcparmory-pinecone -- docker run --rm -i ghcr.io/mcparmory/pinecone:1.0.2
{
"mcpServers": {
"com-mcparmory-pinecone": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pinecone:1.0.2"
]
}
}
} {
"servers": {
"com-mcparmory-pinecone": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pinecone:1.0.2"
]
}
}
} codex mcp add com-mcparmory-pinecone -- docker run --rm -i ghcr.io/mcparmory/pinecone:1.0.2
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-mcparmory-pinecone": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pinecone:1.0.2"
],
"enabled": true
}
}
} mcp_servers:
com-mcparmory-pinecone:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/mcparmory/pinecone:1.0.2"] {
"McpServers": {
"com-mcparmory-pinecone": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pinecone:1.0.2"
]
}
}
} {
"mcpServers": {
"com-mcparmory-pinecone": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/pinecone:1.0.2"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 −3
- Stability: pass → 0.77 functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −2
- Stability: pass → 0.80 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed oci/ghcr.io/mcparmory/pinecone:1.0.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
create_backup Create Backup ~161
Create a backup of a Pinecone index to preserve its current state. Backups can be named and described for easy identification and management.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | The API version specified as a date-based header (required for all requests). Use the default version 2026-04 unless you need a specific earlier version. |
| description | string | – | An optional description of the backup. Use this to document the purpose or context of the backup for future reference. |
| index_name | string | yes | The name of the index to back up. This identifies which index will be backed up. |
| name | string | – | An optional name for the backup. If provided, this will be used to identify the backup in your backup list. |
No output schema declared.
No examples provided.
create_collection Create Collection ~158
Create a new collection in Pinecone by specifying a name and source index. Collections allow you to organize and manage data within an index (note: serverless indexes do not support collections).
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date-based header in YYYY-MM format. Defaults to 2026-04 if not provided. |
| name | string | yes | The name for the new collection. Must be 1-45 characters long, start and end with an alphanumeric character, and contain only lowercase alphanumeric characters or hyphens. |
| source | string | yes | The name of an existing index to use as the source for this collection. The source index will provide the data and configuration for the collection. |
No output schema declared.
No examples provided.
create_index Create Index ~356
Create a new Pinecone index by specifying vector dimensions, similarity metric, deployment configuration, and optional metadata. This establishes the foundation for storing and searching vectors.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version identifier in date format (e.g., 2026-04). Required for all requests to ensure compatibility. |
| deletion_protection | string | – | Enable or disable deletion protection for the index. When enabled, prevents accidental index removal. Defaults to disabled. |
| dimension | string | – | Number of dimensions for vectors stored in this index (1-20,000). Required for dense vector types. Omit for sparse vectors. |
| metric | string | – | Distance metric for similarity calculations: 'cosine' (default for dense vectors), 'euclidean', or 'dotproduct' (required for sparse vectors). |
| name | string | yes | Unique name for the index (1-45 characters). Must start and end with an alphanumeric character and contain only lowercase letters, numbers, or hyphens. |
| spec | – | yes | Deployment configuration specifying where and how the index runs. For serverless indexes, provide cloud provider and region. For pod-based indexes, specify environment, pod type, and pod size. |
| tags | object | – | Optional custom metadata tags for organizing and identifying the index. Keys up to 80 characters (alphanumeric, underscore, hyphen); values up to 120 characters (alphanumeric, semicolon, at-sign, und… |
| vector_type | string | – | Vector type for the index: 'dense' (default, requires dimension specification) or 'sparse' (omit dimension specification). |
No output schema declared.
No examples provided.
create_index_for_model Create Index for Model ~455
Create a vector search index with integrated embedding capabilities. Pinecone automatically converts your source text using the specified hosted embedding model during data operations, eliminating the need for separate embedding infrastructure.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version identifier in date format (required header for all requests). |
| cloud | string | yes | Cloud provider where the index will be hosted: AWS, Google Cloud, or Azure. |
| deletion_protection | string | – | Enable or disable deletion protection to prevent accidental index removal. Defaults to disabled if not specified. |
| dimension | integer | – | Optional vector dimension size for embeddings. If not specified, the dimension is automatically determined by the selected embedding model. |
| field_map | object | yes | Mapping that identifies which text field from your documents will be embedded. Specify the source field name that contains the text to vectorize. |
| fields | object | yes | Configuration map defining metadata field names and their types. Each field name must be unique and follow valid metadata field naming conventions. |
| metric | string | – | Distance metric for similarity search operations: cosine, euclidean, or dotproduct. If omitted, defaults based on the selected embedding model. Cannot be changed after index creation. |
| model | string | yes | Name of the hosted embedding model to use for automatic text vectorization (e.g., multilingual-e5-large). The model determines default vector dimensions and distance metrics. |
| name | string | yes | Unique name for the index. Must be 1-45 characters, start and end with alphanumeric characters, and contain only lowercase letters, numbers, or hyphens. |
| read_capacity | – | – | Optional capacity configuration for read operations. Defaults to OnDemand mode; specify Dedicated mode with node_type and scaling parameters for predictable, reserved throughput. |
| region | string | yes | Geographic region for index deployment (e.g., us-east-1, europe-west1). Must be a valid region for your chosen cloud provider. |
| tags | object | – | Optional custom key-value tags for organizing and identifying the index. Keys up to 80 characters, values up to 120 characters. Keys must be alphanumeric with underscores or hyphens; values support a… |
No output schema declared.
No examples provided.
create_index_from_backup Create Index From Backup ~275
Create a new index by restoring data from an existing backup. The new index will be initialized with the backup's configuration and data.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date string in YYYY-MM format (e.g., 2026-04). This header is required to ensure compatibility with the API version. |
| backup_id | string | yes | The unique identifier of the backup to restore from, formatted as a UUID. |
| deletion_protection | string | – | Optional setting to prevent accidental deletion of the index. Set to 'enabled' to protect the index or 'disabled' (default) to allow deletion. |
| name | string | yes | The name for the new index. Must be 1-45 characters long, start and end with an alphanumeric character, and contain only lowercase letters, numbers, or hyphens. |
| tags | object | – | Optional custom metadata tags for organizing and identifying the index. Tag keys can be up to 80 characters and must contain only alphanumeric characters, underscores, or hyphens. Tag values can be u… |
No output schema declared.
No examples provided.
delete_backup Delete Backup ~83
Permanently delete a backup by its ID. This operation removes the backup and cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date string in YYYY-MM format (defaults to 2026-04 if not provided). |
| backup_id | string | yes | The unique identifier of the backup to delete, formatted as a UUID. |
No output schema declared.
No examples provided.
delete_collection Delete Collection ~106
Permanently delete an existing collection and all its data. Note that serverless indexes do not support collections.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | Required API version header in date-based format (defaults to 2026-04). This ensures the request is processed with the correct API specification. |
| collection_name | string | yes | The name of the collection to delete (e.g., 'test-collection'). This is a required identifier that specifies which collection will be removed. |
No output schema declared.
No examples provided.
delete_index Delete Index ~92
Permanently delete an existing index and all its data. This operation cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date string in YYYY-MM format (defaults to 2026-04). Required header for request routing. |
| index_name | string | yes | The name of the index to delete (e.g., 'test-index'). Must match an existing index exactly. |
No output schema declared.
No examples provided.
get_backup Get Backup ~111
Retrieve detailed information about a specific backup by its ID. Returns the backup's metadata and configuration.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date-based header to ensure compatibility with the Pinecone API. Defaults to 2026-04 if not provided. |
| backup_id | string | yes | The unique identifier of the backup to retrieve, formatted as a UUID (e.g., 670e8400-e29b-41d4-a716-446655440000). |
No output schema declared.
No examples provided.
get_collection Get Collection ~90
Retrieve detailed metadata and configuration information about a specific collection. Note that serverless indexes do not support collections.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date-based header in YYYY-MM format (defaults to 2026-04 if not provided). |
| collection_name | string | yes | The name of the collection to retrieve information about (e.g., 'tiny-collection'). |
No output schema declared.
No examples provided.
get_index Get Index ~112
Retrieve detailed metadata and configuration information about a specific index, including its dimensions, metric type, and current status.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date in YYYY-MM format. Defaults to 2026-04 if not provided; include this header to ensure compatibility with a specific API version. |
| index_name | string | yes | The name of the index to retrieve. Use the exact index name as it appears in your Pinecone project (e.g., 'test-index'). |
No output schema declared.
No examples provided.
get_restore_job Get Restore Job ~112
Retrieve detailed information about a specific restore job, including its status, progress, and configuration.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date-based header to ensure compatibility with the Pinecone API. Defaults to 2026-04 if not provided. |
| job_id | string | yes | The unique identifier of the restore job to retrieve, formatted as a UUID (e.g., 670e8400-e29b-41d4-a716-446655440000). |
No output schema declared.
No examples provided.
list_collections List Collections ~62
Retrieve all collections in a project. Note that serverless indexes do not support collections.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date string in YYYY-MM format. Required for all requests to ensure compatibility with the API specification. |
No output schema declared.
No examples provided.
list_index_backups List Index Backups ~137
Retrieve all backups for a specified index with pagination support. Use pagination tokens to navigate through large result sets.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date string in YYYY-MM format (defaults to 2026-04). Required for request routing. |
| index_name | string | yes | The name of the index for which to list backups. |
| limit | integer | – | Maximum number of backup results to return per page. Must be between 1 and 100 (defaults to 10). |
| paginationToken | string | – | Pagination token from a previous response to retrieve the next page of results. |
No output schema declared.
No examples provided.
list_indexes List Indexes ~68
Retrieve all indexes in the current project. Returns a list of index configurations and metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date string in YYYY-MM format. Required for request routing and response formatting. Defaults to 2026-04 if not provided. |
No output schema declared.
No examples provided.
list_project_backups List Project Backups ~118
Retrieve all backups for indexes in a project with optional pagination. Use pagination tokens to navigate through large result sets.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date-based string (defaults to 2026-04). Required header for API compatibility. |
| limit | integer | – | Maximum number of backups to return per page, between 1 and 100. Defaults to 10 results per page. |
| paginationToken | string | – | Pagination token from a previous response to retrieve the next page of results. |
No output schema declared.
No examples provided.
list_restore_jobs List Restore Jobs ~128
Retrieve a paginated list of all restore jobs for the project. Use pagination tokens to navigate through results.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | API version specified as a date string in YYYY-MM format. Required for all requests. Defaults to 2026-04. |
| limit | integer | – | Maximum number of restore jobs to return per page, between 1 and 100 results. Defaults to 10 if not specified. |
| paginationToken | string | – | Pagination token from a previous response to retrieve the next page of restore jobs. Omit for the first page. |
No output schema declared.
No examples provided.
update_index Update Index ~249
Update configuration settings for an existing index, including scaling parameters, deletion protection, and custom tags. Only scaling and configuration attributes can be modified; the index's cloud provider and region cannot be changed.
| Name | Type | Req | Description |
|---|---|---|---|
| X-Pinecone-Api-Version | string | yes | Required API version header in date-based format (defaults to 2026-04). |
| deletion_protection | string | – | Enable or disable deletion protection for the index to prevent accidental removal. Defaults to disabled. |
| index_name | string | yes | The name of the index to configure (e.g., 'test-index'). |
| spec | – | – | The deployment specification for the index. Defines how the index is scaled and configured. Only modifiable attributes related to scaling and configuration are supported; cloud provider and region ar… |
| tags | object | – | Custom key-value tags for organizing and labeling the index. Keys must be 80 characters or fewer and contain only alphanumeric characters, underscores, or hyphens. Values must be 120 characters or fe… |
No output schema declared.
No examples provided.
What is the com.mcparmory/pinecone MCP server?
com.mcparmory/pinecone is an MCP server listed in the public MCP registry as com.mcparmory/pinecone. Create and manage vector database indexes, backups, and collections. This page covers its container image (ghcr.io/mcparmory/pinecone:1.0.2).
Is the com.mcparmory/pinecone MCP server safe to use?
com.mcparmory/pinecone scores 49 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 com.mcparmory/pinecone MCP server expose?
com.mcparmory/pinecone exposes 18 tools: list_indexes, create_index, get_index, update_index, delete_index, and 13 more. Their descriptions and schemas cost roughly 2,873 tokens of context every time the server is loaded.
Is the com.mcparmory/pinecone MCP server still maintained?
com.mcparmory/pinecone is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.