Skavio PDF, OCR & Document Processing MCP

skavio_upload_bytes

Idempotent

Upload a small source supplied directly as standard base64 content to the authenticated company's storage. Use for inline documents or media up to49152 decoded bytes; filename identifies the file type, data_base64 contains the bytes, and idempotency_key identifies this exact filename/content. Use skavio_upload for operator-staged larger files. Returns uploads containing source id, detected kind, size_bytes, pages and duration; pass those IDs to skavio_estimate. Identical completed retries replay the upload, changed content conflicts, and uncertain uploads require operator reconciliation. Uploading creates stored input, not a billable processing job.

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": {
      "filename": "<filename>",
      "data_base64": "<data_base64>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "skavio_upload_bytes"
  }
}

Input Schema

Name	Required	Description
`filename`	Yes	Source basename including extension, for example invoice.pdf. No directory separators or URLs; begins with a letter/digit and may contain letters, digits, spaces, underscore, dot or hyphen. For skavio_upload it must already exist in the configured input directory.
`data_base64`	Yes	Standard base64-encoded raw file bytes without a data: URL prefix. Decoded content must be nonempty and no larger than49152 bytes; keep filename extension consistent with the content.
`idempotency_key`	Yes	Caller-selected stable identifier8-128 characters (letters, digits, underscore, dot, colon or hyphen) for exactly one upload or job intent. Reuse the same key with identical arguments after a retry; use a different key only for a genuinely new intent, never to bypass an uncertain outcome.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 27, 2026

addedInput schema / description

Added value: +"Arguments for skavio_upload_bytes. Company and permissions come from the authenticated connection."

addedInput schema / properties / data_base64 / description

Added value: +"Standard base64-encoded raw file bytes without a data: URL prefix. Decoded content must be nonempty and no larger than49152 bytes; keep filename extension consistent with the content."

addedInput schema / properties / filename / description

Added value: +"Source basename including extension, for example invoice.pdf. No directory separators or URLs; begins with a letter/digit and may contain letters, digits, spaces, underscore, dot or hyphen. For skavio_upload it must already exist in the configured input directory."

addedInput schema / properties / idempotency_key / description

Added value: +"Caller-selected stable identifier8-128 characters (letters, digits, underscore, dot, colon or hyphen) for exactly one upload or job intent. Reuse the same key with identical arguments after a retry; use a different key only for a genuinely new intent, never to bypass an uncertain outcome."

First observedOct 27, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the annotations (which only declare readOnly=false, idempotent=true, destructive=false, openWorld=true). It discloses the retry contract — identical completed retries replay, changed content conflicts, uncertain uploads need operator reconciliation — plus the important side-effect boundary that uploading creates stored input rather than a billable job.

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 limits, then alternatives, then return values, then the idempotency contract — a logical order with little filler. It runs long at six sentences and has minor formatting glitches ('up to49152'), but nearly every clause carries operational weight.

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?

There is no output schema, yet the description still tells the agent what comes back (source id, detected kind, size_bytes, pages, duration) and how to use it. Combined with the size ceiling, retry semantics and the non-billable side-effect note, nothing needed to call this correctly 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 100% and already documents each parameter thoroughly, so the baseline is 3. The description adds modest value by binding the three parameters into one intent — filename determines type, data_base64 carries the bytes, and idempotency_key identifies that exact filename/content pair — which the schema states only per-field.

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 and resource — uploading a base64-supplied source into the authenticated company's storage — and immediately scopes it to 'small' inline payloads. It explicitly names the sibling it is not (skavio_upload for operator-staged larger files), so an agent can route correctly without opening either 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 an explicit selection rule: use this for inline documents/media up to 49152 decoded bytes, use skavio_upload for larger staged files. It also names the follow-on step ('pass those IDs to skavio_estimate'), closing the workflow loop rather than leaving the agent to guess.

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

All Skavio PDF, OCR & Document Processing MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.