Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

Run a Cypher graph query

graph_query
Destructive

Run Cypher against a property graph to answer relationship questions, traverse paths and neighbors, run graph algorithms, and write graph changes; returns result rows with execution time.

Instructions

Run Cypher against a database's property graph and return {rows, execution_time_ms}: read with MATCH, write with CREATE, MERGE, SET and DELETE, combine with UNWIND and UNION, and run graph algorithms with CALL gds.<algorithm>(...) YIELD ...; separate several statements with ;. Use it for relationship questions such as paths, neighbors and communities; use query for SQL tables. Write clauses change the graph permanently, and read-only API keys are refused for them.

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": {
      "cypher": "<cypher>"
    },
    "name": "graph_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
cypherYesCypher text with literal values written inline; separate multiple statements with `;`.
paramsNoNot used for binding; write values inline in `cypher`.
databaseNoDatabase whose graph to use (default main).
graph_nameNoReserved; queries always run on the selected database's graph.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.0.1
    • changedInput schema / properties / cypher / description
      Previous value: -"Cypher statement. Multiple `;`-separated statements supported."New value: +"Cypher text with literal values written inline; separate multiple statements with `;`."
    • changedInput schema / properties / database / description
      Previous value: -"Selected tenant database; defaults to main."New value: +"Database whose graph to use (default main)."
    • changedInput schema / properties / graph_name / description
      Previous value: -"Reserved for multi-graph tenants. Currently always the tenant's default graph."New value: +"Reserved; queries always run on the selected database's graph."
    • changedInput schema / properties / params / description
      Previous value: -"Parameters (currently informational only — inline literals work as expected; parameterized bindings land in v1.6.6)."New value: +"Not used for binding; write values inline in `cypher`."
  2. First observedv1.0.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes beyond the annotations (destructiveHint=true, readOnlyHint=false) by stating that write clauses persist permanently AND that read-only API keys are refused for them — an authorization constraint the annotations cannot express. It also discloses multi-statement behavior with `;` and the GDS algorithm invocation form, which materially affect how the call is composed.

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

Conciseness4/5

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

Front-loads the action and return shape before the clause taxonomy and the sibling routing, which is good ordering. The clause enumeration (UNWIND, UNION, GDS YIELD) is dense but each item tells the agent a supported capability, though the sentence runs long and could be split for scanability.

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

Completeness5/5

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

There is no output schema, and the description supplies the return shape itself; there are no annotations for write semantics, and the description covers permanence and key restrictions. Combined with the alternative routing and statement separator, an agent has everything needed to call this correctly.

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 description coverage is 100%, including the non-obvious notes that `params` is not used for binding and that `graph_name` is reserved, so the schema already carries parameter meaning. The description reinforces the inline-literal convention but adds nothing beyond what the schema states, making the baseline 3 correct.

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?

States a specific verb (run Cypher) against a specific resource (a database's property graph) and declares the return shape {rows, execution_time_ms}. It also distinguishes itself from the `query` sibling (SQL tables), so an agent can pick correctly without opening either schema.

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?

Gives explicit when-to-use (relationship questions such as paths, neighbors, communities) and names the alternative for the other case ('use `query` for SQL tables'). It also flags the read/write split within the tool itself, leaving little to inference.

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