Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

Run a read-only SQL query

query
Read-onlyIdempotent

Run read-only SQL SELECT statements to read SynapCores data, including vector similarity searches, with automatic row limits and paging; return results as JSON, Markdown, or CSV.

Instructions

Run a read-only SQL SELECT (or WITH ... SELECT) on a SynapCores database and return the rows. Use it to read data, including vector search over table columns with EMBED() and COSINE_SIMILARITY(); use execute for writes and schema changes (any other statement is rejected here), graph_query for Cypher, and semantic_search for vector collections. When the SQL has no LIMIT, LIMIT limit (default 1000, max 10000) and OFFSET offset are appended. Returns column names and types plus rows as JSON, or a Markdown table or CSV per format.

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": {
      "sql": "<sql>"
    },
    "name": "query"
  }
}

Input Schema

NameRequiredDescriptionDefault
sqlYesA SELECT or WITH statement. Look up syntax and AI functions with `sql_manual`.
limitNoRow cap appended as LIMIT when the SQL has none (default 1000, max 10000).
formatNorows = JSON with columns and rows (default); markdown = a table; csv = comma-separated text.rows
offsetNoRows to skip, appended as OFFSET (default 0); combine with `limit` to page through results.
databaseNoDatabase name; omit to use the default database.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.0.1
    • changedInput schema / properties / database / description
      Previous value: -"Database name (optional, uses default if not specified)"New value: +"Database name; omit to use the default database."
    • changedInput schema / properties / format / description
      Previous value: -"Output format (default: rows)"New value: +"rows = JSON with columns and rows (default); markdown = a table; csv = comma-separated text."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum rows to return (default: 1000, max: 10000)"New value: +"Row cap appended as LIMIT when the SQL has none (default 1000, max 10000)."
    • changedInput schema / properties / offset / description
      Previous value: -"Number of rows to skip"New value: +"Rows to skip, appended as OFFSET (default 0); combine with `limit` to page through results."
    • changedInput schema / properties / sql / description
      Previous value: -"SQL SELECT query to execute"New value: +"A SELECT or WITH statement. Look up syntax and AI functions with `sql_manual`."
  2. First observedv1.0.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is covered; the description adds material behavior beyond them: implicit LIMIT/OFFSET injection when SQL has no LIMIT, the default 1000 and hard max 10000, and statement rejection. It does not discuss cost, timeouts, or error behavior on invalid SQL, so not a 5.

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 dense sentences, front-loaded with the core action and the sibling routing, then behavioral detail on limit injection and return format. No redundant restatement of the title or schema.

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?

No output schema exists, and the description compensates by describing the return shape (column names and types plus rows, as JSON, Markdown, or CSV). It covers parameter interplay and rejection rules; minor gaps remain around error cases and query cost, but nothing essential for correct invocation is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds operational meaning: limit is appended only when the SQL lacks a LIMIT and is capped at 10000, offset is appended for paging, and format controls the return encoding. Database defaulting is covered in the schema only.

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 and resource ('Run a read-only SQL SELECT (or WITH ... SELECT) on a SynapCores database and return the rows') and immediately marks the boundary that only SELECT/WITH is accepted. An agent can distinguish it from execute, graph_query, and semantic_search without opening the 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?

Explicitly routes the agent: use this to read data, use `execute` for writes and schema changes, `graph_query` for Cypher, `semantic_search` for vector collections. It also names the exclusion rule ('any other statement is rejected here'), which is the when-not condition.

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