The Unstructured API MCP server enables comprehensive management of data extraction and processing pipelines with these capabilities:
Source Management: Create, list, update, and delete source connectors (S3, Azure, Google Drive).
Destination Management: Create, list, update, and delete destination connectors (S3, Weaviate, AstraDB, Neo4j, MongoDB).
Workflow Operations: Build, run, update, and delete customizable workflows with configurable DAG nodes for partitioning, chunking, prompting, and embedding.
Job Control: List, retrieve details, and cancel workflow jobs.
Firecrawl Integration: Start and manage web crawling jobs and LLM-optimized text generation for HTML content.
Debugging Tools: Use MCP Inspector and logging for troubleshooting.
Terminal Access: Optional Desktop Commander for advanced file operations.
Used for loading environment variables from a .env file, specifically for storing and accessing the Unstructured API key
Serves as the implementation language for the MCP server, with specific dependencies including unstructured-client for API interaction
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Unstructured API MCP Server list my recent workflows"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This server interacts with the Unstructured API to manage sources, destinations, and workflows. It is not actively maintained and is kept here for reference.
If you want to parse and transform files into structured output (markdown, JSON, HTML, or plain text), use the Unstructured Transform MCP server instead.
Unstructured Transform brings production-grade document processing to your agents as a hosted MCP server. It gives them the ability to turn 60+ file types into structured data that's ready for your applications, vector databases, and any downstream processes by parsing, enriching, chunking, and embedding files directly inside their current session.
You can start using it by signing up here.
An MCP server implementation for interacting with the Unstructured API. This server provides tools to list sources and workflows.
Tool | Description |
| Lists available sources from the Unstructured API. |
| Get detailed information about a specific source connector. |
| Create a source connector.) |
| Update an existing source connector by params. |
| Delete a source connector by source id. |
| Lists available destinations from the Unstructured API. |
| Get detailed info about a specific destination connector |
| Create a destination connector by params. |
| Update an existing destination connector by destination id. |
| Delete a destination connector by destination id. |
| Lists workflows from the Unstructured API. |
| Get detailed information about a specific workflow. |
| Create a new workflow with source, destination id, etc. |
| Run a specific workflow with workflow id |
| Update an existing workflow by params. |
| Delete a specific workflow by id. |
| Lists jobs for a specific workflow from the Unstructured API. |
| Get detailed information about a specific job by job id. |
| Delete a specific job by id. |
| Lists all workflows that have any completed job, together with information about source and destination details. |
Below is a list of connectors the UNS-MCP server currently supports, please see the full list of source connectors that Unstructured platform supports here and destination list here. We are planning on adding more!
Source | Destination |
S3 | S3 |
Azure | Weaviate |
Google Drive | Pinecone |
OneDrive | AstraDB |
Salesforce | MongoDB |
Sharepoint | Neo4j |
Databricks Volumes | |
Databricks Volumes Delta Table |
To use the tool that creates/updates/deletes a connector, the credentials for that specific connector must be defined in your .env file. Below is the list of credentials for the connectors we support:
Credential Name | Description |
| required to run the |
| required to create S3 connector via |
| required to create Weaviate vector db connector, see how in documentation |
| required to use Firecrawl tools in |
| required to create Astradb connector via |
| required option 1 to create Azure connector via |
| required option 2 to create Azure connector via |
| required option 3 to create Azure connector via |
| required to create Neo4j connector via |
| required to create Mongodb connector via |
| a string value. The original server account key (follow documentation) is in json file, run |
| required to create Databricks volume/delta table connector via |
| required to create One Drive connector via |
| required to create Pinecone vector DB connector via |
| required to create salesforce source connector via |
| required to create One Drive connector via |
| Used to set logging level for our |
| set to true so that |
| set to true so that |
Firecrawl is a web crawling API that provides two main capabilities in our MCP:
HTML Content Retrieval: Using invoke_firecrawl_crawlhtml to start crawl jobs and check_crawlhtml_status to monitor them
LLM-Optimized Text Generation: Using invoke_firecrawl_llmtxt to generate text and check_llmtxt_status to retrieve results
How Firecrawl works:
Web Crawling Process:
Starts with a specified URL and analyzes it to identify links
Uses the sitemap if available; otherwise follows links found on the website
Recursively traverses each link to discover all subpages
Gathers content from every visited page, handling JavaScript rendering and rate limits
Jobs can be cancelled with cancel_crawlhtml_job if needed
Use this if you require all the info extracted into raw HTML, Unstructured's workflow cleans it up really well :smile:
LLM Text Generation:
After crawling, extracts clean, meaningful text content from the crawled pages
Generates optimized text formats specifically formatted for large language models
Results are automatically uploaded to the specified S3 location
Note: LLM text generation jobs cannot be cancelled once started. The cancel_llmtxt_job function is provided for consistency but is not currently supported by the Firecrawl API.
Note: A FIRECRAWL_API_KEY environment variable must be set to use these functions.
Related MCP server: MCP REST API Server
This guide provides step-by-step instructions to set up and configure the UNS_MCP server using Python 3.12 and the uv tool.
Python 3.12+
uv for environment management
An API key from Unstructured. You can sign up and obtain your API key here.
uv (Recommended)No additional installation is required when using uvx as it handles execution. However, if you prefer to install the package directly:
uv pip install uns_mcpFor integration with Claude Desktop, add the following content to your claude_desktop_config.json:
Note: The file is located in the ~/Library/Application Support/Claude/ directory.
Using uvx Command:
{
"mcpServers": {
"UNS_MCP": {
"command": "uvx",
"args": ["uns_mcp"],
"env": {
"UNSTRUCTURED_API_KEY": "<your-key>"
}
}
}
}Alternatively, Using Python Package:
{
"mcpServers": {
"UNS_MCP": {
"command": "python",
"args": ["-m", "uns_mcp"],
"env": {
"UNSTRUCTURED_API_KEY": "<your-key>"
}
}
}
}Clone the repository.
Install dependencies:
uv syncSet your Unstructured API key as an environment variable. Create a .env file in the root directory with the following content:
UNSTRUCTURED_API_KEY="YOUR_KEY" Refer to .env.template for the configurable environment variables.
You can now run the server using one of the following methods:
uvx pip install -e .Update your Claude Desktop config:
{
"mcpServers": {
"UNS_MCP": {
"command": "uvx",
"args": ["uns_mcp"]
}
}
}Note: Remember to point to the uvx executable in environment where you installed the package
Note: Not supported by Claude Desktop.
For SSE protocol, you can debug more easily by decoupling the client and server:
Start the server in one terminal:
uv run python uns_mcp/server.py --host 127.0.0.1 --port 8080
# or
make sse-serverTest the server using a local client in another terminal:
uv run python minimal_client/client.py "http://127.0.0.1:8080/sse"
# or
make sse-clientNote: To stop the services, use Ctrl+C on the client first, then the server.
Configure Claude Desktop to use stdio:
{
"mcpServers": {
"UNS_MCP": {
"command": "ABSOLUTE/PATH/TO/.local/bin/uv",
"args": [
"--directory",
"ABSOLUTE/PATH/TO/YOUR-UNS-MCP-REPO/uns_mcp",
"run",
"server.py"
]
}
}
}Alternatively, run the local client:
uv run python minimal_client/client.py uns_mcp/server.pyConfigure the minimal client using environmental variables:
LOG_LEVEL="ERROR": Set to suppress debug outputs from the LLM, displaying clear messages for users.
CONFIRM_TOOL_USE='false': Disable tool use confirmation before execution. Use with caution, especially during development, as LLM may execute expensive workflows or delete data.
Anthropic provides MCP Inspector tool to debug/test your MCP server. Run the following command to spin up a debugging UI. From there, you will be able to add environment variables (pointing to your local env) on the left pane. Include your personal API key there as env var. Go to tools, you can test out the capabilities you add to the MCP server.
mcp dev uns_mcp/server.pyIf you need to log request call parameters to UnstructuredClient, set the environment variable DEBUG_API_REQUESTS=false.
The logs are stored in a file with the format unstructured-client-{date}.log, which can be examined to debug request call parameters to UnstructuredClient functions.
We are going to use @wonderwhy-er/desktop-commander to add terminal access to the minimal client. It is built on the MCP Filesystem Server. Be careful, as the client (also LLM) now has access to private files.
Execute the following command to install the package:
npx @wonderwhy-er/desktop-commander setupThen start client with extra parameter:
uv run python minimal_client/client.py "http://127.0.0.1:8080/sse" "@wonderwhy-er/desktop-commander@^0.2.11"
# or
make sse-client-terminalIf your client supports using only subset of tools here are the list of things you should be aware:
update_workflow tool has to be loaded in the context together with create_workflow tool, because it contains detailed description on how to create and configure custom node.
update_workflow - needs to have in context the configuration of the workflow it is updating either by providing it by the user or by calling get_workflow_info tool, as this tool doesn't work as patch applier, it fully replaces the workflow config.
Any new developed features/fixes/enhancements will be added to CHANGELOG.md. 0.x.x-dev pre-release format is preferred before we bump to a stable version.
If you encounter issues with Error: spawn <command> ENOENT it means <command> is not installed or visible in your PATH:
Make sure to install it and add it to your PATH.
or provide absolute path to the command in the command field of your config. So for example replace python with /opt/miniconda3/bin/python
Cancel an in-progress Firecrawl HTML crawl job.
Args:
crawl_id: ID of the crawl job to cancel
Returns:
Dictionary containing the result of the cancellation
Inputs: crawl_id (required). Returns: result
Delete a specific job.
Args:
job_id: ID of the job to cancel
Returns:
String containing the response from the job cancellation
Inputs: job_id (required). Returns: result
Check the status of an existing Firecrawl HTML crawl job.
Args:
crawl_id: ID of the crawl job to check
Returns:
Dictionary containing the current status of the crawl job
Inputs: crawl_id (required). Returns: result
Check the status of an existing llmfull.txt generation job.
Args:
job_id: ID of the llmfull.txt generation job to check
Returns:
Dictionary containing the current status of the job and text content if completed
Inputs: job_id (required). Returns: result
Create a destination connector based on type.
Args:
ctx: Context object with the request and lifespan context
name: A unique name for this connector
destination_type: The type of destination being created
type_specific_config:
astradb:
collection_name: The AstraDB collection name
keyspace: The AstraDB keyspace
batch_size: (Optional[int]) The batch size for inserting documents
databricks_delta_table:
catalog: Name of the catalog in Databricks Unity Catalog
database: The database in Unity Catalog
http_path: The cluster’s or SQL warehouse’s HTTP Path value
server_hostname: The Databricks cluster’s or SQL warehouse’s Server Hostname value
table_name: The name of the table in the schema
volume: Name of the volume associated with the schema.
schema: (Optional[str]) Name of the schema associated with the volume
volume_path: (Optional[str]) Any target folder path within the volume, starting
from the root of the volume.
databricks_volumes:
catalog: Name of the catalog in Databricks
host: The Databricks host URL
volume: Name of the volume associated with the schema
schema: (Optional[str]) Name of the schema associated with the volume. The default
value is "default".
volume_path: (Optional[str]) Any target folder path within the volume,
starting from the root of the volume.
mongodb:
database: The name of the MongoDB database
collection: The name of the MongoDB collection
neo4j:
database: The Neo4j database, e.g. "neo4j"
uri: The Neo4j URI e.g. neo4j+s://<neo4j_instance_id>.databases.neo4j.io
batch_size: (Optional[int]) The batch size for the connector
pinecone:
index_name: The Pinecone index name
namespace: (Optional[str]) The pinecone namespace, a folder inside the
pinecone index
batch_size: (Optional[int]) The batch size
s3:
remote_url: The S3 URI to the bucket or folder
weaviate:
cluster_url: URL of the Weaviate cluster
collection: Name of the collection in the Weaviate cluster
Note: Minimal schema is required for the collection, e.g. record_id: Text
Returns:
String containing the created destination connector information
Inputs: name (required), destination_type (required), type_specific_config (required). Returns: result
Create a source connector based on type. Args: ctx: Context object with the request and lifespan context name: A unique name for this connector source_type: The type of source being created (e.g., 'azure', 'onedrive', 'salesforce', 'gdrive', 's3', 'sharepoint')
type_specific_config:
azure:
remote_url: The Azure Storage remote URL with the format
az://<container-name>/<path/to/file/or/folder/in/container/as/needed>
recursive: (Optional[bool]) Whether to access subfolders
gdrive:
drive_id: The Drive ID for the Google Drive source
recursive: (Optional[bool]) Whether to access subfolders
extensions: (Optional[list[str]]) File extensions to filter
onedrive:
path: The path to the target folder in the OneDrive account
user_pname: The User Principal Name (UPN) for the OneDrive user account
recursive: (Optional[bool]) Whether to access subfolders
authority_url: (Optional[str]) The authentication token provider URL
s3:
remote_url: The S3 URI to the bucket or folder (e.g., s3://my-bucket/)
recursive: (Optional[bool]) Whether to access subfolders
salesforce:
username: The Salesforce username
categories: (Optional[list[str]]) Optional Salesforce domain,the names of the
Salesforce categories (objects) that you want to access, specified as
a comma-separated list. Available categories include Account, Campaign,
Case, EmailMessage, and Lead.
sharepoint:
site: The SharePoint site to connect to
user_pname: The username for the SharePoint site
path: (Optional) The path within the SharePoint site
recursive: (Optional[bool]) Whether to access subfolders
authority_url: (Optional[str]) The authority URL for authentication
Returns:
String containing the created source connector information
Inputs: name (required), source_type (required), type_specific_config (required). Returns: result
Create a new workflow.
Args:
workflow_config: A Typed Dictionary containing required fields (destination_id - should be a
valid UUID, name, source_id - should be a valid UUID, workflow_type) and non-required fields
(schedule, and workflow_nodes). Note workflow_nodes is only enabled when workflow_type
is `custom` and is a list of WorkflowNodeTypedDict: partition, prompter,chunk, embed
Below is an example of a partition workflow node:
{
"name": "vlm-partition",
"type": "partition",
"sub_type": "vlm",
"settings": {
"provider": "your favorite provider",
"model": "your favorite model"
}
}
Returns:
String containing the created workflow informationCustom workflow DAG nodes
If WorkflowType is set to custom, you must also specify the settings for the workflow’s directed acyclic graph (DAG) nodes. These nodes’ settings are specified in the workflow_nodes array.
A Source node is automatically created when you specify the source_id value outside of the workflow_nodes array.
A Destination node is automatically created when you specify the destination_id value outside of the workflow_nodes array.
You can specify Partitioner, Chunker, Prompter, and Embedder nodes.
The order of the nodes in the workflow_nodes array will be the same order that these nodes appear in the DAG, with the first node in the array added directly after the Source node. The Destination node follows the last node in the array.
Be sure to specify nodes in the allowed order. The following DAG placements are all allowed:
Source -> Partitioner -> Destination,
Source -> Partitioner -> Chunker -> Destination,
Source -> Partitioner -> Chunker -> Embedder -> Destination,
Source -> Partitioner -> Prompter -> Chunker -> Destination,
Source -> Partitioner -> Prompter -> Chunker -> Embedder -> Destination
Partitioner node A Partitioner node has a type of partition and a subtype of auto, vlm, hi_res, or fast.
Examples:
auto strategy: { "name": "Partitioner", "type": "partition", "subtype": "vlm", "settings": { "provider": "anthropic", (required) "model": "claude-sonnet-4-20250514", (required) "output_format": "text/html", "user_prompt": null, "format_html": true, "unique_element_ids": true, "is_dynamic": true, "allow_fast": true } }
vlm strategy: Allowed values are provider and model. Below are examples: - "provider": "anthropic" "model": "claude-sonnet-4-20250514", - "provider": "openai" "model": "gpt-4o"
hi_res strategy: { "name": "Partitioner", "type": "partition", "subtype": "unstructured_api", "settings": { "strategy": "hi_res", "include_page_breaks": <true|false>, "pdf_infer_table_structure": <true|false>, "exclude_elements": [ "", "" ], "xml_keep_tags": <true|false>, "encoding": "", "ocr_languages": [ "", "" ], "extract_image_block_types": [ "image", "table" ], "infer_table_structure": <true|false> } }
fast strategy { "name": "Partitioner", "type": "partition", "subtype": "unstructured_api", "settings": { "strategy": "fast", "include_page_breaks": <true|false>, "pdf_infer_table_structure": <true|false>, "exclude_elements": [ "", "" ], "xml_keep_tags": <true|false>, "encoding": "", "ocr_languages": [ "", "" ], "extract_image_block_types": [ "image", "table" ], "infer_table_structure": <true|false> } }
Chunker node A Chunker node has a type of chunk and subtype of chunk_by_character or chunk_by_title.
chunk_by_character { "name": "Chunker", "type": "chunk", "subtype": "chunk_by_character", "settings": { "include_orig_elements": <true|false>, "new_after_n_chars": , (required, if not provided
set same as max_characters) "max_characters": , (required) "overlap": , (required, if not provided set default to 0) "overlap_all": <true|false>, "contextual_chunking_strategy": "v1" } }
chunk_by_title { "name": "Chunker", "type": "chunk", "subtype": "chunk_by_title", "settings": { "multipage_sections": <true|false>, "combine_text_under_n_chars": , "include_orig_elements": <true|false>, "new_after_n_chars": , (required, if not provided
set same as max_characters) "max_characters": , (required) "overlap": , (required, if not provided set default to 0) "overlap_all": <true|false>, "contextual_chunking_strategy": "v1" } }
Prompter node An Prompter node has a type of prompter and subtype of:
openai_image_description,
anthropic_image_description,
bedrock_image_description,
vertexai_image_description,
openai_table_description,
anthropic_table_description,
bedrock_table_description,
vertexai_table_description,
openai_table2html,
openai_ner
Example: { "name": "Prompter", "type": "prompter", "subtype": "", "settings": {} }
Embedder node An Embedder node has a type of embed
Allowed values for subtype and model_name include:
"subtype": "azure_openai"
"model_name": "text-embedding-3-small"
"model_name": "text-embedding-3-large"
"model_name": "text-embedding-ada-002"
"subtype": "bedrock"
"model_name": "amazon.titan-embed-text-v2:0"
"model_name": "amazon.titan-embed-text-v1"
"model_name": "amazon.titan-embed-image-v1"
"model_name": "cohere.embed-english-v3"
"model_name": "cohere.embed-multilingual-v3"
"subtype": "togetherai":
"model_name": "togethercomputer/m2-bert-80M-2k-retrieval"
"model_name": "togethercomputer/m2-bert-80M-8k-retrieval"
"model_name": "togethercomputer/m2-bert-80M-32k-retrieval"
Example: { "name": "Embedder", "type": "embed", "subtype": "", "settings": { "model_name": "" } }
Inputs: workflow_config (required). Returns: result
Delete a destination connector.
Args:
destination_id: ID of the destination connector to delete
Returns:
String containing the result of the deletion
Inputs: destination_id (required). Returns: result
Delete a source connector.
Args:
source_id: ID of the source connector to delete
Returns:
String containing the result of the deletion
Inputs: source_id (required). Returns: result
Delete a specific workflow.
Args:
workflow_id: ID of the workflow to delete
Returns:
String containing the response from the workflow deletion
Inputs: workflow_id (required). Returns: result
Get detailed information about a specific destination connector.
Args:
destination_id: ID of the destination connector to get information for
Returns:
String containing the destination connector information
Inputs: destination_id (required). Returns: result
Get detailed information about a specific job.
Args:
job_id: ID of the job to get information for
Returns:
String containing the job information
Inputs: job_id (required). Returns: result
Get detailed information about a specific source connector.
Args:
source_id: ID of the source connector to get information for, should be valid UUID
Returns:
String containing the source connector information
Inputs: source_id (required). Returns: result
Get detailed information about a specific workflow.
Args:
workflow_id: ID of the workflow to get information for
Returns:
String containing the workflow information
Inputs: workflow_id (required). Returns: result
Start an asynchronous web crawl job using Firecrawl to retrieve HTML content.
Args:
url: URL to crawl
s3_uri: S3 URI where results will be uploaded
limit: Maximum number of pages to crawl (default: 100)
Returns:
Dictionary with crawl job information including the job ID
Inputs: url (required), s3_uri (required), limit. Returns: result
Start an asynchronous llmfull.txt generation job using Firecrawl. This file is a standardized markdown file containing information to help LLMs use a website at inference time. The llmstxt endpoint leverages Firecrawl to crawl your website and extracts data using gpt-4o-mini Args: url: URL to crawl s3_uri: S3 URI where results will be uploaded max_urls: Maximum number of pages to crawl (1-100, default: 10)
Returns:
Dictionary with job information including the job ID
Inputs: url (required), s3_uri (required), max_urls. Returns: result
List available destinations from the Unstructured API.
Args:
destination_type: Optional destination connector type to filter by
Returns:
String containing the list of destinations
Inputs: destination_type. Returns: result
List jobs via the Unstructured API.
Args:
workflow_id: Optional workflow ID to filter by
status: Optional job status to filter by
Returns:
String containing the list of jobs
Inputs: workflow_id, status. Returns: result
List available sources from the Unstructured API.
Args:
source_type: Optional source connector type to filter by
Returns:
String containing the list of sources
Inputs: source_type. Returns: result
List workflows from the Unstructured API.
Args:
destination_id: Optional destination connector ID to filter by
source_id: Optional source connector ID to filter by
status: Optional workflow status to filter by
Returns:
String containing the list of workflows
Inputs: destination_id, source_id, status. Returns: result
List workflows with finished jobs via the Unstructured API.
Args:
source_type: Optional source connector type to filter by
destination_type: Optional destination connector type to filter by
Returns:
String containing the list of workflows with finished jobs and source and destination
details
Inputs: source_type, destination_type. Returns: result
Transform a local file into structured data using the Unstructured API.
Args:
input_file_path: The absolute path to the file.
output_file_dir: The absolute path to the directory where the output file should be saved.
strategy: The strategy for transformation.
Available strategies:
VLM - most advanced transformation suitable for difficult PDFs and Images
hi_res - high resolution transformation suitable for most document types
fast - fast transformation suitable for PDFs with extractable text
auto - automatically choose the best strategy based on the input file
vlm_model: The VLM model to use for the transformation.
vlm_model_provider: The VLM model provider to use for the transformation.
output_type: The type of output to generate. Options: 'json' for json
or 'md' for markdown.
Returns:
A string containing the structured data or a message indicating the output file
path with the structured data.
Inputs: input_file_path (required), output_file_dir (required), strategy, vlm_model, +2 more. Returns: result
Run a specific workflow.
Args:
workflow_id: ID of the workflow to run
Returns:
String containing the response from the workflow execution
Inputs: workflow_id (required). Returns: result
Update a destination connector based on type.
Args:
ctx: Context object with the request and lifespan context
destination_id: ID of the destination connector to update
destination_type: The type of destination being updated
type_specific_config:
astradb:
collection_name: (Optional[str]): The AstraDB collection name
keyspace: (Optional[str]): The AstraDB keyspace
batch_size: (Optional[int]) The batch size for inserting documents
databricks_delta_table:
catalog: (Optional[str]): Name of the catalog in Databricks Unity Catalog
database: (Optional[str]): The database in Unity Catalog
http_path: (Optional[str]): The cluster’s or SQL warehouse’s HTTP Path value
server_hostname: (Optional[str]): The Databricks cluster’s or SQL warehouse’s
Server Hostname value
table_name: (Optional[str]): The name of the table in the schema
volume: (Optional[str]): Name of the volume associated with the schema.
schema: (Optional[str]) Name of the schema associated with the volume
volume_path: (Optional[str]) Any target folder path within the volume, starting
from the root of the volume.
databricks_volumes:
catalog: (Optional[str]): Name of the catalog in Databricks
host: (Optional[str]): The Databricks host URL
volume: (Optional[str]): Name of the volume associated with the schema
schema: (Optional[str]) Name of the schema associated with the volume. The default
value is "default".
volume_path: (Optional[str]) Any target folder path within the volume,
starting from the root of the volume.
mongodb:
database: (Optional[str]): The name of the MongoDB database
collection: (Optional[str]): The name of the MongoDB collection
neo4j:
database: (Optional[str]): The Neo4j database, e.g. "neo4j"
uri: (Optional[str]): The Neo4j URI
e.g. neo4j+s://<neo4j_instance_id>.databases.neo4j.io
batch_size: (Optional[int]) The batch size for the connector
pinecone:
index_name: (Optional[str]): The Pinecone index name
namespace: (Optional[str]) The pinecone namespace, a folder inside the
pinecone index
batch_size: (Optional[int]) The batch size
s3:
remote_url: (Optional[str]): The S3 URI to the bucket or folder
weaviate:
cluster_url: (Optional[str]): URL of the Weaviate cluster
collection: (Optional[str]): Name of the collection in the Weaviate cluster
Note: Minimal schema is required for the collection, e.g. record_id: Text
Returns:
String containing the updated destination connector information
Inputs: destination_id (required), destination_type (required), type_specific_config (required). Returns: result
Update a source connector based on type.
Args:
ctx: Context object with the request and lifespan context
source_id: ID of the source connector to update
source_type: The type of source being updated (e.g., 'azure', 'onedrive',
'salesforce', 'gdrive', 's3', 'sharepoint')
type_specific_config:
azure:
remote_url: (Optional[str]) The Azure Storage remote URL with the format
az://<container-name>/<path/to/file/or/folder/in/container/as/needed>
recursive: (Optional[bool]) Whether to access subfolders
gdrive:
drive_id: (Optional[str]) The Drive ID for the Google Drive source
recursive: (Optional[bool]) Whether to access subfolders
extensions: (Optional[list[str]]) File extensions to filter
onedrive:
path: (Optional[str]) The path to the target folder in the OneDrive account
user_pname: (Optional[str]) The User Principal Name (UPN) for the OneDrive
user account
recursive: (Optional[bool]) Whether to access subfolders
authority_url: (Optional[str]) The authentication token provider URL
s3:
remote_url: (Optional[str]) The S3 URI to the bucket or folder
(e.g., s3://my-bucket/)
recursive: (Optional[bool]) Whether to access subfolders
salesforce:
username: (Optional[str]) The Salesforce username
categories: (Optional[list[str]]) Optional Salesforce domain,the names of the
Salesforce categories (objects) that you want to access, specified as
a comma-separated list. Available categories include Account, Campaign,
Case, EmailMessage, and Lead.
sharepoint:
site: Optional([str]) The SharePoint site to connect to
user_pname: Optional([str]) The username for the SharePoint site
path: (Optional) The path within the SharePoint site
recursive: (Optional[bool]) Whether to access subfolders
authority_url: (Optional[str]) The authority URL for authentication
Returns:
String containing the updated source connector information
Inputs: source_id (required), source_type (required), type_specific_config (required). Returns: result
Update an existing workflow.
Args:
workflow_id: ID of the workflow to update
workflow_config: A Typed Dictionary containing required fields (destination_id,
name, source_id, workflow_type) and non-required fields (schedule, and workflow_nodes)
Returns:
String containing the updated workflow information
Inputs: workflow_id (required), workflow_config (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 26 tools
Most tools have distinct purposes targeting specific resources like connectors, workflows, jobs, and local files, with clear separation between source/destination connectors and workflow operations. However, some ambiguity exists between cancel_job and cancel_crawlhtml_job, as both cancel jobs but for different job types, which could cause confusion without careful reading of descriptions.
Tool names follow a highly consistent verb_noun pattern throughout, such as create_destination_connector, list_workflows, and update_source_connector. All tools use snake_case with clear action-object pairs, making the naming predictable and easy to understand across the entire set.
With 26 tools, the count feels heavy for the server's purpose of managing unstructured data workflows, connectors, and jobs. While the domain is broad, the tool set includes many specific operations (e.g., separate tools for checking status of different job types) that could potentially be consolidated, making it borderline excessive but still manageable.
The tool set provides comprehensive coverage for the unstructured data processing domain, including full CRUD operations for connectors and workflows, job management with status checks and cancellation, workflow execution, and local file partitioning. There are no obvious gaps, and the tools support end-to-end workflows from source to destination with various processing nodes.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
