Skip to main content
Glama
Obsideo MCP server

Obsideo MCP server

by Regan-Milne

Retrieve an object

get
Destructive

Retrieve and decrypt stored objects by key; small text returns inline, or save bytes to local_path (overwrites existing file).

Instructions

Retrieve an object. Encrypted objects (the default for anything stored through this server) are decrypted automatically with the local key; retrieval from a machine without that key will fail, which is the intended property. Small text objects return inline; pass local_path for anything else. WRITES TO DISK: passing local_path writes the bytes to that path and overwrites any existing file there, so treat it as a write operation and confirm the path with your human first.

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": {
      "key": "<key>"
    },
    "name": "get"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYes
local_pathNoSave to this path instead of returning inline. Overwrites an existing file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.7
    • changedInput schema / properties / local_path / description
      Previous value: -"Save to this path instead of returning inline"New value: +"Save to this path instead of returning inline. Overwrites an existing file."
  2. First observedv0.2.0

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds substantial context beyond that: default encryption of stored objects and automatic decryption with the local key, the intended failure on a keyless machine, inline-vs-disk return behavior, and overwrite semantics. The 'treat it as a write operation and confirm the path' instruction is exactly the behavioral guidance needed for a destructive-capable tool.

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 core action, then layered with the most consequential constraint (encryption failure) and the write warning in caps. Dense but every clause earns its place; the encryption sentence is long but carries necessary failure-mode information.

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 two-parameter tool with no output schema and rich annotations, the description covers the failure modes, return-mode switch, and disk-write consequences an agent needs before calling it. Nothing material 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 50% and the schema already documents local_path, but the description adds real meaning: that local_path is for non-small-text objects, that it overwrites, and that the path must be confirmed with a human. The required key parameter remains undocumented in both schema and description, so a small gap persists.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Retrieve) and resource (an object) keyed by a single required parameter, so an agent knows it is a read-by-key operation. It is slightly generic about what an 'object' is and does not differentiate itself from siblings such as ls or put, which keeps it below a 5.

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 clear conditional guidance: small text objects come back inline, while anything else should use local_path. It also imposes a confirmation step with the human before writing. It does not name alternatives like ls for listing or explain when not to use it at all.

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