Skip to main content
Glama

Teable MCP (Official)

get-records

Read-onlyIdempotent

For DATA QUERIES (search, filter, paginate). For current view rows, use get-grid-rows.

Parameters:

  • tableId (required)

  • viewId - Apply view filters (optional)

  • recordId - Fetch a specific record by ID. When provided, search/take/skip are ignored (optional)

  • take - Records to return, default 100, max 1000 (optional)

  • skip - Records to skip for pagination (optional)

  • projection - Field IDs or names to return (optional). If not provided, only first 50 fields will be returned

  • search - Search filter object: { value: "keyword", fieldId: "Name" } (fieldId accepts field name OR ID; omit for global search) (optional)

Important:

  • If user refers to rows in current view ("first 3 rows", "last row", "row N"), use get-grid-rows instead.

  • This tool queries server-persisted data. For the user's live view state (unsaved filters/sorts), use get-grid-rows.

Response (tabular format): {header: ["id", "Name"], rows: [["rec001", "Task A"]]}

Examples: All: { tableId: "tblXXX" } By ID: { tableId: "tblXXX", recordId: "recXXX" } Search: { tableId: "tblXXX", search: { value: "keyword", fieldId: "Name" } } Pagination: { tableId: "tblXXX", take: 50, skip: 100 }

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": {
      "tableId": "<tableId>",
      "projection": "<projection>"
    },
    "name": "get-records"
  }
}

Input Schema

NameRequiredDescriptionDefault
skipNoNumber of records to skip for pagination
takeNoNumber of records to return (default: 100, max: 1000)
searchNoSearch filter. Pass { value: "keyword" } for global search, or { value: "keyword", fieldId: "Name" } to search a specific field
viewIdNoView ID to use for filtering (optional)
tableIdYesThe ID of the table to query records from
recordIdNoRecord ID to fetch a specific record directly. When provided, search/take/skip are ignored.
projectionYesProjection of field ids to return, pass "all" to return all fields (max 50)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already establish read-only/idempotent safety, but the description adds genuinely new behavioral facts: data is server-persisted (not live view state), recordId short-circuits search/take/skip precedence, and projection omission silently truncates to the first 50 fields. It also shows the tabular response shape, which no output schema provides.

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?

Well front-loaded: purpose sentence, then alternatives, then parameters, then response, then examples. Slightly redundant in restating take's default/max twice (parameter list and schema mirror), but every section serves a distinct reader need.

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?

For a 7-parameter query tool with no output schema and a nested search object, the description supplies the response shape, the truncation default for projection, the precedence rules, and per-mode examples. Nothing an agent needs to call it correctly 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% and already documents defaults and bounds, so the baseline is 3. The description goes beyond by giving worked invocation examples for each mode and clarifying the precedence rule (recordId ignores search/take/skip) and the 'all' projection escape hatch, though it repeats some schema-stated defaults.

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?

Opens with a specific verb and resource cluster ('DATA QUERIES (search, filter, paginate)') and immediately differentiates from the sibling get-grid-rows. An agent can tell which tool to pick 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?

Explicitly states when to use this tool (server-persisted data queries) and when not to (current-view rows, live/unsaved view state), naming get-grid-rows as the alternative twice with concrete trigger phrases like 'first 3 rows' and 'row N'.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources