MCP Mistral OCR Optimized
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OCR_DIR | Yes | Required directory path where files to be processed are located. | |
| BATCH_MODE | No | Batch processing mode selection: auto, always, or never. | auto |
| EXTRACT_FOOTER | No | Whether to extract document footers by default. | false |
| EXTRACT_HEADER | No | Whether to extract document headers by default. | false |
| INCLUDE_IMAGES | No | Whether to include base64 images in the OCR output by default. | false |
| BATCH_MIN_FILES | No | Minimum number of files required to use batch processing in auto mode. | 5 |
| MISTRAL_API_KEY | Yes | Required Mistral AI API key for OCR processing. | |
| DEFAULT_TABLE_FORMAT | No | Default format for tables in OCR output: null, markdown, or html. | markdown |
| INLINE_BATCH_THRESHOLD | No | Threshold for using inline batch processing (for less than 10 files). | 10 |
| MAX_CONCURRENT_REQUESTS | No | Maximum number of concurrent API requests. | 5 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_toolsB | List available OCR tools. |
| process_local_fileC | Process a single local file from OCR_DIR. |
| process_batch_local_filesC | Process multiple local files concurrently. |
| process_url_fileC | Process a file from a URL. |
| create_batch_jobC | Create a batch processing job for large file sets. |
| check_batch_statusC | Check the status of a batch processing job. |
| download_batch_resultsC | Download results from a completed batch job. |
| cancel_batch_jobC | Cancel a running batch job. |
| list_batch_jobsC | List batch jobs with optional filtering. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose with no overlap: batch job management (cancel, check, create, download, list), tool listing, and file processing (batch local, single local, URL). The descriptions clearly differentiate between batch operations and individual file processing, eliminating any ambiguity.
All tools follow a consistent verb_noun pattern with snake_case throughout (e.g., cancel_batch_job, process_local_file). The naming is predictable and readable, with no deviations in style or convention across the toolset.
With 9 tools, the count is well-scoped for an OCR server covering batch processing, individual file handling, and job management. Each tool earns its place by addressing specific needs without redundancy or excessive fragmentation.
The toolset provides strong coverage for OCR workflows, including CRUD-like operations for batch jobs (create, list, check, cancel, download) and file processing (local and URL). A minor gap is the lack of tools for configuring OCR settings or handling errors, but core operations are well-covered.