Skip to main content
Glama
Obsideo MCP server

Obsideo MCP server

by Regan-Milne

Start Obsideo signup (or claim the trial)

signup_start

Initiates Obsideo signup by emailing a 6-digit verification code to a real inbox, claiming a configured no-email trial in place or creating a new account.

Instructions

Start Obsideo signup: emails a 6-digit verification code (8 GB free, no card, no expiry; 16 GB after the account holder answers eight questions in the Drive web app). If a no-email trial is configured on this machine, this CLAIMS it in place: same account, bucket, keys and data, only the quota rises. Otherwise it creates a new account for the email. Use a real inbox you or your human can read; documentation placeholders and disposable domains are refused with labeled errors. Then call signup_verify.

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": {
      "email": "<email>"
    },
    "name": "signup_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailYesReal email address; it is the account identity
sourceNoWhere you found Obsideo (defaults to 'mcp')
abandon_trialNoOnly when the email already has its own account (email_in_use): sign in to that account instead of claiming; the trial and its data are left behind.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.2

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover readOnly/openWorld/idempotent/destructive flags; the description adds real substance on top: an email is dispatched, quota is 8 GB free then 16 GB after eight questions, claiming preserves the same account/bucket/keys/data with only quota rising, and disposable/placeholder domains are rejected with labeled errors. It does not mention throttling, code expiry, or what a repeat call does.

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 the action and effect, then the quota parenthetical, then the claim branch, then the next-step call. Dense but every sentence carries information; the nested parenthetical about the eight questions is the only mildly cluttered part.

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 state-mutating signup tool with no output schema, it covers what gets created, what email is sent, quota expectations, the trial-claim path, error conditions, and the exact next tool to call. Nothing an agent needs in order to invoke it correctly is missing.

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 100% and each parameter is already documented, so the schema carries the parameter burden. The description reinforces the constraint that email must be a readable real inbox (disposable domains refused) and that abandon_trial abandons the trial, but adds no syntax or format detail beyond the schema.

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+resource ('Start Obsideo signup'), names the side effect (emails a 6-digit code), and explicitly separates the two modes: claiming a pre-configured no-email trial vs. creating a new account for the email. It is clearly distinguishable from siblings signup_verify and trial.

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?

Gives a clear entry condition (need a real inbox you or your human can read), names the follow-up step ('Then call signup_verify'), and explains the claim-vs-create branch. It stops short of stating when to prefer this over the sibling 'trial' or 'portal' tools, or what to do when an account already exists (that is only implied via abandon_trial).

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