Skip to main content
Glama
tigergraph

tigergraph-mcp

Official
by tigergraph
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

tigergraph__load_vectors_from_json

Bulk-load vectors from a local JSON Lines file into a vertex type's vector attribute by creating and running a GSQL loading job, then removing the job.

Instructions

Bulk-load vectors from a JSON Lines (.jsonl) file into a vertex type's vector attribute. Creates a GSQL loading job with JSON_FILE="true", runs it with the file, then drops the job.

File format: Each line is a JSON object with an ID field and a vector field. The vector is stored as a comma-separated string (not a JSON array).

Example file (id_key='id', vector_key='embedding'):

{"id": "vertex1", "embedding": "0.1,0.2,0.3"}
{"id": "vertex2", "embedding": "0.4,0.5,0.6"}

Prerequisites:

  1. Vertex type must already exist

  2. Vector attribute must already be added (use 'add_vector_attribute')

  3. File must exist on the local machine (it is uploaded to TigerGraph via REST)

Related Tools: add_vector_attribute, load_vectors_from_csv (CSV alternative), upsert_vectors (REST API for in-memory data), get_vector_index_status (check indexing after load)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
id_keyNoJSON key for the vertex ID. Default: 'id'.id
profileNoConnection profile name. Omit to use the active default profile. Use 'list_connections' to see available profiles.
file_pathYesAbsolute path to the JSON Lines (.jsonl) file on the local machine (uploaded to TigerGraph via REST). Each line is a JSON object with an ID field and a vector field.
graph_nameNoName of the graph. If not provided, uses default connection.
vector_keyNoJSON key for the vector data (stored as a comma-separated string). Default: 'vector'.vector
vertex_typeYesTarget vertex type that has the vector attribute.
vector_attributeYesName of the vector attribute to load into.
element_separatorNoSeparator between vector elements within the vector string value. Default: ','.,

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.2

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (non-read-only, non-idempotent, non-destructive), the description discloses the full lifecycle: creates a GSQL loading job, runs it, then drops it. It also warns that the file is uploaded to TigerGraph via REST and that vectors must be comma-separated strings, not JSON arrays.

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?

The first sentence states the core action, and the rest is organized under File format, Example, Prerequisites, and Related Tools. No filler; it is detailed but still scannable.

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?

The description covers format, prerequisites, process, and alternatives. It does not state what response or status is returned, but it is otherwise complete for a complex multi-parameter tool, and the related get_vector_index_status suggests a post-check.

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

Parameters4/5

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

Input schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds real value by showing a concrete file example with id_key and vector_key, clarifying the comma-separated string representation, and explaining element_separator usage.

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

Purpose5/5

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

The opening sentence names the exact operation: bulk-load vectors from a .jsonl file into a vector attribute, including the mechanism (create, run, drop a GSQL load job). It specifically says JSON Lines, which distinguishes it from the CSV sibling.

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

Usage Guidelines5/5

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

Prerequisites are explicit (vertex type, vector attribute, local file), and Related Tools names the CSV alternative, the in-memory REST API path, and the post-load index check. The description also calls out the id_key/vector_key convention with an example.

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

Deploy Server

Other Tools