Skip to main content
Glama
io.github.avaazquezz/mcp-qdrant

io.github.avaazquezz/mcp-qdrant

by avaazquezz

Get Qdrant collection info

qdrant_collection_info
Read-onlyIdempotent

Retrieves full configuration and status for a specific Qdrant collection, returning a clear error when the collection does not exist.

Instructions

Return full config and status of one collection.

    Fails with a clear error if the collection doesn't exist.

    Example: {"collection_name": "docs"}
    

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "collection_name": "<collection_name>"
    },
    "name": "qdrant_collection_info"
  }
}

Input Schema

NameRequiredDescriptionDefault
collection_nameYes

Output Schema

NameRequiredDescriptionDefault
configYesCurrent statistics and configuration of the collection
statusYesCurrent statistics and configuration of the collection
warningsNoWarnings related to the collection
created_atNoTime of the collection creation. Absent for collections created before Qdrant started recording it.
points_countNoApproximate number of points (vectors + payloads) in collection. Each point could be accessed by unique id.
update_queueNoUpdate queue info
payload_schemaYesTypes of stored payload
segments_countYesNumber of segments in collection. Each segment has independent vector as payload indexes
optimizer_statusYesCurrent statistics and configuration of the collection
indexed_vectors_countNoApproximate number of indexed vectors in the collection. Indexed vectors in large segments are faster to query, as it is stored in a specialized vector index.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed23 schema fields changedv2.12.0
    • addedOutput schema / $defs / BoolIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].price`. The field must be inside the array&#x27;s elements. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • addedOutput schema / $defs / CollectionParams / properties / id_tracker
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/IdTrackerParams"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Configuration of the point id tracker"
      +}
    • changedOutput schema / $defs / Datatype / enum
      Previous value: -[
      -  "float32",
      -  "uint8",
      -  "float16",
      -  "turbo4"
      -]New value: +[
      +  "float32",
      +  "uint8",
      +  "float16",
      +  "turbo4",
      +  "turbo8",
      +  "turbo16"
      +]
    • addedOutput schema / $defs / DatetimeIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].price`. The field must be inside the array&#x27;s elements. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • addedOutput schema / $defs / FloatIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].price`. The field must be inside the array&#x27;s elements. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • addedOutput schema / $defs / GeoIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].price`. The field must be inside the array&#x27;s elements. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • changedOutput schema / $defs / HnswConfig / properties / m / description
      Previous value: -"Number of edges per node in the index graph. Larger the value - more accurate the search, more space required."New value: +"Number of edges per node in the index graph. Larger the value - more accurate the search, more space required. Set to 0 to disable the main HNSW graph. Additional payload-aware links may still be built when the effective payload M is positive (see payload_m). This setting alone does not guarantee exact search."
    • changedOutput schema / $defs / HnswConfig / properties / payload_m / description
      Previous value: -"Custom M param for hnsw graph built for payload index. If not set, default M will be used."New value: +"Number of additional payload-aware links per node. If unset, the value of m is used. An effective value of 0 disables these additional links. A positive value allows them for indexed payload fields with HNSW enabled, even when m is 0."
    • changedOutput schema / $defs / HnswConfigDiff / properties / m / description
      Previous value: -"Number of edges per node in the index graph. Larger the value - more accurate the search, more space required."New value: +"Number of edges per node in the index graph. Larger the value - more accurate the search, more space required. Set to 0 to disable the main HNSW graph. Additional payload-aware links may still be built when the effective payload M is positive (see payload_m). This setting alone does not guarantee exact search."
    • changedOutput schema / $defs / HnswConfigDiff / properties / payload_m / description
      Previous value: -"Custom M param for additional payload-aware HNSW links. If not set, default M will be used."New value: +"Number of additional payload-aware links per node. If unset, the value of m is used. An effective value of 0 disables these additional links. A positive value allows them for indexed payload fields with HNSW enabled, even when m is 0."
    • addedOutput schema / $defs / IdTrackerParams
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Params of the point id tracker",
      +  "properties": {
      +    "memory": {
      +      "anyOf": [
      +        {
      +          "$ref": "#/$defs/Memory"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "default": null,
      +      "description": "Memory placement of the point id mapping in indexed segments: `cold` keeps it on disk and reads it on demand, `cached` keeps it on disk but primes the page cache with it on load, `pinned` keeps it in RAM. Default: `pinned`."
      +    }
      +  },
      +  "title": "IdTrackerParams",
      +  "type": "object"
      +}
    • addedOutput schema / $defs / IntegerIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].price`. The field must be inside the array&#x27;s elements. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • addedOutput schema / $defs / KeywordIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].price`. The field must be inside the array&#x27;s elements. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • changedOutput schema / $defs / OptimizersConfig / properties / max_segment_size / description
      Previous value: -"Do not create segments larger this size (in kilobytes). Large segments might require disproportionately long indexation times, therefore it makes sense to limit the size of segments.  If indexing speed is more important - make this parameter lower. If search speed is more important - make this parameter higher. Note: 1Kb = 1 vector of size 256 If not set, will be automatically selected considering the number of available CPUs."New value: +"Do not create segments larger than this size (in kilobytes). Large segments might require disproportionately long indexation times, therefore it makes sense to limit the size of segments.  If indexing speed is more important - make this parameter lower. If search speed is more important - make this parameter higher. Note: 1Kb = 1 vector of size 256 If not set, will be automatically selected considering the number of available CPUs."
    • addedOutput schema / $defs / TextIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].title`. The field must be inside the array&#x27;s elements. Every query on the field, not only nested filters, treats each element as its own document: a condition matches a point when a single element matches it, and BM25 scores elements separately. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • addedOutput schema / $defs / TextIndexParams / properties / scoring
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "boolean"
      +    },
      +    {
      +      "$ref": "#/$defs/TextScoringParams"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Enable ranking points by BM25 over this field; `true` for the defaults. Changing it rebuilds the index. Default: disabled.",
      +  "title": "Scoring"
      +}
    • addedOutput schema / $defs / TextScoringParams
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Parameters of ranking over a text index. The index records the length of each document, which BM25 normalizes by. `k1` and `b` are set per query.",
      +  "properties": {
      +    "type": {
      +      "$ref": "#/$defs/TextScoringType",
      +      "description": "Parameters of ranking over a text index. The index records the length of each document, which BM25 normalizes by. `k1` and `b` are set per query."
      +    }
      +  },
      +  "required": [
      +    "type"
      +  ],
      +  "title": "TextScoringParams",
      +  "type": "object"
      +}
    • addedOutput schema / $defs / TextScoringType
      Added value: +{
      +  "description": "How a text index ranks documents.",
      +  "enum": [
      +    "bm25"
      +  ],
      +  "title": "TextScoringType",
      +  "type": "string"
      +}
    • changedOutput schema / $defs / TokenizerType / enum
      Previous value: -[
      -  "prefix",
      -  "whitespace",
      -  "word",
      -  "multilingual"
      -]New value: +[
      +  "prefix",
      +  "whitespace",
      +  "word",
      +  "multilingual",
      +  "code"
      +]
    • changedOutput schema / $defs / TurboQuantBitSize / enum
      Previous value: -[
      -  "bits1",
      -  "bits1_5",
      -  "bits2",
      -  "bits4"
      -]New value: +[
      +  "bits1",
      +  "bits1_5",
      +  "bits2",
      +  "bits4",
      +  "bits8"
      +]
    • addedOutput schema / $defs / UuidIndexParams / properties / nested
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Index every object of this array as a separate entry, e.g. `offers` for the field `offers[].price`. The field must be inside the array&#x27;s elements. `is_empty` on the field matches a point when one of its elements lacks the field, and never a point without elements. Default: disabled.",
      +  "title": "Nested"
      +}
    • changedOutput schema / $defs / VectorParams / properties / datatype / description
      Previous value: -"Defines which datatype should be used to represent vectors in the storage. Choosing different datatypes allows to optimize memory usage and performance vs accuracy.  - For `float32` datatype - vectors are stored as single-precision floating point numbers, 4 bytes. - For `float16` datatype - vectors are stored as half-precision floating point numbers, 2 bytes. - For `uint8` datatype - vectors are stored as unsigned 8-bit integers, 1 byte. It expects vector elements to be in range `[0, 255]`. - For `turbo4` datatype - vectors are quantized to 4 bits per element using the TurboQuant algorithm."New value: +"Defines which datatype should be used to represent vectors in the storage. Choosing different datatypes allows to optimize memory usage and performance vs accuracy.  - For `float32` datatype - vectors are stored as single-precision floating point numbers, 4 bytes. - For `float16` datatype - vectors are stored as half-precision floating point numbers, 2 bytes. - For `uint8` datatype - vectors are stored as unsigned 8-bit integers, 1 byte. It expects vector elements to be in range `[0, 255]`. - For `turbo4` datatype - vectors are quantized to 4 bits per element using the TurboQuant algorithm. - For `turbo8` datatype - vectors are quantized to 8 bits per element using the TurboQuant algorithm. - For `turbo16` datatype - vectors are quantized to 16 bits per element using the TurboQuant algorithm."
    • addedOutput schema / properties / created_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "format": "date-time",
      +      "type": "string"
      +    },
      +    {
      +      "format": "date",
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Time of the collection creation. Absent for collections created before Qdrant started recording it.",
      +  "title": "Created At"
      +}
  2. First observedv1.1.1

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered structurally. The description adds one genuinely new behavioral fact — that it fails with a clear error on a missing collection — but says nothing about the potential size of the config/status payload or rate considerations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short lines: what it returns, how it fails, and a concrete input example. Nothing wasteful, and the primary purpose is front-loaded in the first sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A single-parameter read tool with an output schema, so return values needn't be explained, and the error behavior is disclosed. The only remaining gap is routing guidance against the collection_list and collection_exists siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the schema only declares collection_name as a required string with no explanation. The description's example {"collection_name": "docs"} clarifies that the value is the collection name string rather than an ID or alias, which is real added meaning, but naming rules and format are still unstated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: "Return full config and status of one collection." The phrase "one collection" signals it is scoped to a single item, which implicitly separates it from the sibling qdrant_collection_list, though no sibling is named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the phrase "full config and status" — an agent can infer this is the deep-inspection tool for a known collection. There is no explicit when-to-use or when-not guidance, and no mention of the alternatives qdrant_collection_exists or qdrant_collection_list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.