Skip to main content
Glama
Praroop1435

Airtable Full-Stack MCP

by Praroop1435
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

airtable_query_records

Query Airtable records using server-side formula filters, field selection, sorting, and automatic pagination. Retrieve matched record IDs and values for analysis or downstream actions.

Instructions

Queries records from an Airtable table with server-side formula filtering, field selection, sorting, and pagination.

When to Use

  • When searching for specific records matching criteria (e.g. stage, status, date range, or email).

  • When retrieving record IDs, computed formulas, or linked fields for downstream analysis or updates.

  • When inspecting current data density and values across an Airtable base.

When NOT to Use

  • Do NOT use this tool to modify or delete records. Use 'airtable_manage_records' or 'airtable_batch_upsert' instead.

  • Do NOT use this tool to inspect table column schemas. Use 'airtable_list_schema' instead.

Operational Disclosures

  • Side Effects: Read-only. Safe to invoke repeatedly with zero mutations to the base.

  • Filtering: Supports standard Airtable formula syntax (e.g. AND({Status} = 'Active', {Balance} > 0)).

  • Pagination: Automatically paginates using Airtable offset tokens up to max_records.

  • Auth Scopes: Requires Personal Access Token with 'data.records:read' scope.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoSort criteria, e.g. [{"field": "Created", "direction": "desc"}]
viewNoSpecific View name or ID to filter by view configuration
fieldsNoSpecific field names to return (saves bandwidth and token usage)
base_idYesAirtable Base ID (starts with app, e.g. appoorUuG6wgx8dJ1)
max_recordsNoMaximum total records to retrieve across pages (default: 100)
table_name_or_idYesTarget Table Name or Table ID
filter_by_formulaNoAirtable formula to filter records server-side, e.g. "AND({Stage} = 'Pending', {Amount} > 100)"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.1.1
    • changedInput schema / properties / base_id / description
      Previous value: -"Airtable Base ID (starts with app...)"New value: +"Airtable Base ID (starts with app, e.g. appoorUuG6wgx8dJ1)"
    • changedInput schema / properties / fields / description
      Previous value: -"Specific field names to return (saves bandwidth)"New value: +"Specific field names to return (saves bandwidth and token usage)"
    • changedInput schema / properties / filter_by_formula / description
      Previous value: -"Airtable formula to filter records server-side (e.g. AND({Status} = 'Active', {Stage} = 'Live'))"New value: +"Airtable formula to filter records server-side, e.g. \"AND({Stage} = 'Pending', {Amount} > 100)\""
    • changedInput schema / properties / max_records / description
      Previous value: -"Maximum number of records to retrieve (default 100)"New value: +"Maximum total records to retrieve across pages (default: 100)"
    • changedInput schema / properties / sort / description
      Previous value: -"Sort criteria: [{ field: string, direction?: \"asc\" | \"desc\" }]"New value: +"Sort criteria, e.g. [{\"field\": \"Created\", \"direction\": \"desc\"}]"
    • changedInput schema / properties / sort / items / properties / direction / description
      Previous value: -"Sort direction"New value: +"Sort direction: \"asc\" or \"desc\""
    • addedInput schema / properties / view
      Added value: +{
+  "description": "Specific View name or ID to filter by view configuration",
+  "type": "string"
+}
  2. First observedv1.0.0

TDQS

A4.8/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden, and it delivers: it states the tool is read-only with zero mutations, describes automatic pagination using offset tokens, discloses the required auth scope, and gives filtering syntax details. This exceeds what an agent would need to safely invoke it.

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 description is well-structured with clear headings, front-loaded purpose, and compact bullet lists. Every section adds practical value: when to use, when not to use, and operational disclosures. There is no filler or repetition of schema details.

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?

For a 7-parameter tool with no output schema and no annotations, the description covers the critical operational context: read-only behavior, auth scope, pagination, filtering, and sibling routing. It stops short of explicitly describing the return shape or error/rate-limit behavior, which would make it fully complete, but the provided guidance is sufficient for correct invocation.

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?

The schema already documents all 7 parameters at 100% coverage, so the baseline is 3. The description adds meaningful extra semantics: it explains formula syntax with an example, clarifies pagination behavior up to max_records, and emphasizes server-side filtering, which goes beyond the raw parameter names and schema descriptions.

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 description opens with a specific verb and resource: 'Queries records from an Airtable table' and enumerates the exact capabilities: server-side formula filtering, field selection, sorting, and pagination. It clearly distinguishes itself from mutation tools and schema tools by naming those alternatives in the usage guidance.

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?

There is an explicit 'When to Use' section listing concrete scenarios, and an explicit 'When NOT to Use' section naming the correct alternatives: airtable_manage_records, airtable_batch_upsert, and airtable_list_schema. This leaves no ambiguity about when to select this tool over siblings.

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