akb

akb_create_table

Create a structured data table in a vault by defining columns, types, indexes, and unique keys. Optionally place it in a collection to appear beside related documents, or leave it at the vault root.

Instructions

Create a structured data table in a vault. The response carries the canonical uri — akb://{vault}/coll/{collection}/table/{name} when stored under a collection, or akb://{vault}/table/{name} at the vault root. Tables live alongside documents inside collections and follow the same permissions. Define columns with name and type (text, number, boolean, date, json). Optional collection (e.g. 'sessions/learnings') groups the table under that collection so it appears beside the documents and files there in akb_browse; omit for vault root.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Table name (unique within the vault)
`vault`	No	Target vault name. Required unless `parent` is given.
`parent`	No	Parent location as a canonical URI — `akb://{vault}` for the vault root, `akb://{vault}/coll/{path}` for a collection. When given, the table is created there and `vault`/`collection` are derived from the URI.
`columns`	Yes	Column definitions
`indexes`	No	Declarative lookup (btree) indexes. Each item is {name?, columns}. A column is a bare string or {name, order} where order is 'asc' (default) or 'desc'. Unique indexes are expressed via `unique_keys`, not here.
`collection`	No	Collection path (e.g. 'specs' or 'sessions/learnings'). Omit for vault root. Ignored when `parent` is given.
`description`	No
`unique_keys`	No	Declarative UNIQUE keys. Each item is {name?, columns}. `columns` is a list of existing column names (single or composite). `name` is optional — when omitted AKB generates a deterministic, stable name. Use this (not `indexes`) for unique indexes.
`if_not_exists`	No	When true, an existing table is NOT an error: returns created=false instead of a 409 conflict. Nothing is altered either way. If you also hold READ access to the vault the response carries the STORED schema plus matches_request and mismatches[], so divergence from your spec is explicit; a write-only credential gets only {kind, name, created, outcome}. Must be a real boolean — the string "true" is rejected. Default false keeps the 409.
`_vault_skill_ack`	No	Opaque acknowledgement returned as vault_skill.ack_token. After applying that guide, retry the unchanged operation with this value. The bundled proxy supplies it automatically.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedv2.0.14Sep 3, 2026

addedInput schema / properties / _vault_skill_ack

Added value: +{
+  "description": "Opaque acknowledgement returned as vault_skill.ack_token. After applying that guide, retry the unchanged operation with this value. The bundled proxy supplies it automatically.",
+  "maxLength": 128,
+  "type": "string"
+}

addedInput schema / properties / if_not_exists

Added value: +{
+  "default": false,
+  "description": "When true, an existing table is NOT an error: returns created=false instead of a 409 conflict. Nothing is altered either way. If you also hold READ access to the vault the response carries the STORED schema plus matches_request and mismatches[], so divergence from your spec is explicit; a write-only credential gets only {kind, name, created, outcome}. Must be a real boolean — the string \"true\" is rejected. Default false keeps the 409.",
+  "type": "boolean"
+}

Changed2 schema fields changedv2.0.13Aug 7, 2026

addedInput schema / properties / indexes

Added value: +{
+  "description": "Declarative lookup (btree) indexes. Each item is {name?, columns}. A column is a bare string or {name, order} where order is 'asc' (default) or 'desc'. Unique indexes are expressed via `unique_keys`, not here.",
+  "items": {
+    "properties": {
+      "columns": {
+        "items": {
+          "oneOf": [
+            {
+              "type": "string"
+            },
+            {
+              "properties": {
+                "name": {
+                  "type": "string"
+                },
+                "order": {
+                  "enum": [
+                    "asc",
+                    "desc"
+                  ],
+                  "type": "string"
+                }
+              },
+              "required": [
+                "name"
+              ],
+              "type": "object"
+            }
+          ]
+        },
+        "minItems": 1,
+        "type": "array"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "columns"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / unique_keys

Added value: +{
+  "description": "Declarative UNIQUE keys. Each item is {name?, columns}. `columns` is a list of existing column names (single or composite). `name` is optional — when omitted AKB generates a deterministic, stable name. Use this (not `indexes`) for unique indexes.",
+  "items": {
+    "properties": {
+      "columns": {
+        "items": {
+          "type": "string"
+        },
+        "minItems": 1,
+        "type": "array"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "columns"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed4 schema fields changedv2.0.7Jun 9, 2026

changedInput schema / properties / collection / description

Previous value: -"Collection path (e.g. 'specs' or 'sessions/learnings'). Omit for vault root."New value: +"Collection path (e.g. 'specs' or 'sessions/learnings'). Omit for vault root. Ignored when `parent` is given."

addedInput schema / properties / parent

Added value: +{
+  "description": "Parent location as a canonical URI — `akb://{vault}` for the vault root, `akb://{vault}/coll/{path}` for a collection. When given, the table is created there and `vault`/`collection` are derived from the URI.",
+  "type": "string"
+}

addedInput schema / properties / vault / description

Added value: +"Target vault name. Required unless `parent` is given."

changedInput schema / required

Previous value: -[
-  "vault",
-  "name",
-  "columns"
-]New value: +[
+  "name",
+  "columns"
+]

Addedv2.0.4May 27, 2026
Removedv2.0.1May 21, 2026
First observedv0.1.0May 16, 2026

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses the response URI shape, permission inheritance from collections, and browse visibility. But it does not mention duplicate-name conflict behavior, write permissions required, or other side effects beyond creation, leaving notable gaps.

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?

Every sentence earns its place: purpose, URI shape, placement semantics, column shape, and collection guidance. It is dense but not bloated, and the most essential information is front-loaded.

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 10-parameter creation tool with no annotations and no output schema, the description covers the core action, return URI, permissions, and placement. The detailed schema fills most remaining gaps, but the description could have explicitly guided vault/parent selection and noted conflict behavior to be fully self-sufficient.

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 coverage is 90%, so the baseline is 3. The description adds meaning for `collection` by tying it to the URI path and browse visibility, and it reinforces column structure. It does not substantially clarify `parent`, `indexes`, or `unique_keys` beyond what the schema already says.

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: 'Create a structured data table in a vault.' It clearly differentiates this from sibling tools like akb_create_vault, akb_create_collection, and akb_put by naming the artifact type and giving the canonical URI structure.

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

Usage Guidelines4/5

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

It gives clear placement guidance: use `collection` to group the table under a collection, omit it for vault root, and expects tables to live alongside documents. It does not explicitly contrast with akb_alter_table or akb_drop_table, nor state prerequisites like vault existence, so it stops short of a 5.

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

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dnotitia/akb'

If you have feedback or need assistance with the MCP directory API, please join our Discord server