Skip to main content
Glama
Regan-Milne

Obsideo MCP server

by Regan-Milne
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

Store an object

put
Destructive

Save local files or inline content as encrypted objects with your own key, then replicate across three providers with ongoing integrity verification.

Instructions

Store a local file or inline content as an object. ENCRYPTED BY DEFAULT: the bytes are encrypted client-side with AES-256-GCM using a locally generated, user-held key before they leave the machine, so the platform stores ciphertext it cannot read. The key lives only in the local config file and Obsideo has no copy: if the user loses it the data is unrecoverable, so tell them to back it up. Pass encrypt=false only when another tool must read the stored bytes directly (S3 interop); that stores plaintext. Zero-byte objects are rejected. Objects are replicated to 3 providers and verified on a continuous cryptographic challenge cycle. The first call on a fresh machine also creates the account and can take 20 to 50 seconds; progress is reported while it runs. Encrypted objects are readable only with this machine's key: there is no cross-user sharing of encrypted objects.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesObject key, e.g. backups/db-2026-07-19.sql.zst
contentNoInline UTF-8 content (alternative to local_path)
encryptNoDefaults to true. Set false to store plaintext for S3 interop.
local_pathNoPath of a local file to upload

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.2
    • changedInput schema / properties / encrypt / description
      Previous value: -"Encrypt client-side before upload"New value: +"Defaults to true. Set false to store plaintext for S3 interop."
  2. First observedv0.2.0

TDQS

A4.4/5.0
Behavior5/5

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

The description richly discloses client-side AES-256-GCM encryption, local-only key custody, irrecoverability on key loss, zero-byte rejection, 3-provider replication, continuous verification, first-call account creation delay, and lack of cross-user sharing. This far exceeds the sparse annotations and gives an agent the critical security and latency expectations.

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 long but each sentence delivers essential security, validation, or performance information stole. The most important fact, encryption by default, is front-loaded in ALL CAPS, and the supporting caveats follow in a logical order with no filler.

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?

The description covers encryption, key backup, the plaintext exception, zero-byte limits, replication, first-call latency, and sharing restrictions, leaving little ambiguity for a storage operation. The only notable gap is that it does not state the exact success return value, but that is non-critical for a put operation with no output schema.

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 description coverage is 100%, so each parameter is already explained structurally. The description adds minor context such as zero-byte rejection and the key-loss implication, but it does not substantially expand parameter meaning 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?

The opening line, 'Store a local file or inline content as an object', gives a specific verb, a clear resource, and the two supported input forms. This distinguishes it from sibling read/list/delete tools such as get, ls, and rm without requiring schema inspection.

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?

The core usage is unmistakable, and the description explicitly limits the one major deviation: 'Pass encrypt=false only when another tool must read the stored bytes directly (S3 interop)'. It does not explicitly name alternatives like get or rm for non-use cases, but the storage intent and encryption caveat provide adequate operational guidance.

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