Skip to main content
Glama

muninn_table_publish

DestructiveIdempotent

Publish a table's records as a live public data feed and page - use when the user says publish this table, share this table, put this board online, give me a URL for this data, or wants a chart or dashboard to read a table without an agent copying it. Returns an unguessable munn.is link that serves the named fields as JSON at /raw and as a rendered table at . The copy stays LIVE: adding or editing a record updates what the link serves. The fields to publish must be named: there is no way to publish every field, a field added later stays out until you publish again naming it, and a field marked private is refused. Records are capped at 1000 and a large table finishes assembling over one or more muninn_table_refresh calls. Optionally pass name for a readable address under the user's handle (if the account cannot take that name, the token link is published instead), password to gate it, and expiresAt to make it stop. muninn_table_unpublish revokes it. CONFIRMATION IS REQUIRED: call it first WITHOUT confirmed. That call publishes nothing and returns a preview (the table, the fields that would be public, the record count, name, password and expiry). Show the user that preview, and call again with confirmed:true and the same arguments only after the user says yes. Never set confirmed:true on a first call.

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": {
      "tableSlug": "<tableSlug>",
      "fields": "<fields>"
    },
    "name": "muninn_table_publish"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoOptional readable name, e.g. 'worklist' - becomes <handle>.munn.is/worklist. Letters, numbers and hyphens only. If the name is not available to this account, publishing still succeeds with the token link.
fieldsYesThe exact field keys to publish, in the order the page shows them. Required, with no wildcard: this is the allowlist, and it is the whole safety of the feature. Private fields are refused by name.
passwordNoOptional password a reader must type before the page opens, and before /raw answers. Only pass one the user actually stated. It can never be read back - say it to the user now.
confirmedNoSet true ONLY after the user has seen this tool's preview (table, public fields, record count) and said yes. Omitted or false: nothing is published, and the preview comes back.
expiresAtNoOptional ISO 8601 moment the feed stops serving. Pass null to remove an existing expiry.
tableSlugYesWhich table to publish.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / confirmed
      Added value: +{
      +  "description": "Set true ONLY after the user has seen this tool's preview (table, public fields, record count) and said yes. Omitted or false: nothing is published, and the preview comes back.",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"Optional readable name, e.g. 'worklist' - becomes <handle>.munn.is/worklist. Letters, numbers and hyphens only. A new or changed name needs the Paid plan; publishing itself does not. Publishing still succeeds if the name is rejected."New value: +"Optional readable name, e.g. 'worklist' - becomes <handle>.munn.is/worklist. Letters, numbers and hyphens only. If the name is not available to this account, publishing still succeeds with the token link."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and openWorldHint=true; the description goes well past them by disclosing that the published copy is live and updates on record edits, that publishing is allowlist-only with no wildcard, that later-added fields stay out until republished, that private fields are refused, that records cap at 1000 and large tables finish across muninn_table_refresh calls, that name collisions fall back to the token link, and that a password can never be read back. It also spells out the preview-then-confirm protocol, which is the exact safe-invocation procedure for a destructive, world-visible action.

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-loaded with purpose and trigger phrases, then constraints, then the confirmation protocol in caps — a sensible ordering with no filler sentences. It runs long and repeats the confirm-first rule already stated in the `confirmed` schema field ('Never set confirmed:true on a first call'), which is mild redundancy for a safety-critical action.

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 destructive, world-visible mutation with no output schema, the description covers what the return values are (link, /raw path, preview contents), the side effects (live data exposure, irreversibility of a leaked password), scale limits, and the required consent flow. An agent has everything needed to call it correctly and safely on the first attempt.

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 real meaning the schema only gestures at: it frames `fields` as the entire safety mechanism of the feature, warns that a password is write-only and must be shown to the user immediately, and explains that an unusable `name` silently degrades to the token link rather than failing. The `confirmed` semantics are restated from the schema rather than extended, which keeps it just short of a 5.

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?

Names a specific verb and resource ('Publish a table's records as a live public data feed and page') and immediately distinguishes itself from related tools by describing the output artifact: an unguessable munn.is link serving JSON at /raw and a rendered table. The revocation counterpart (muninn_table_unpublish) is named, so an agent can place the tool among its siblings without opening a 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 concrete user phrasings that select this tool ('publish this table', 'put this board online', 'give me a URL for this data', 'wants a chart or dashboard to read a table without an agent copying it') and names the alternative for the reverse operation. It also states the mandatory two-call confirmation flow, which is the decisive when-to-use rule for this tool.

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