1.15.3npm · @andrea9293/mcp-documentation-server · current release
Observed 2026-08-14T06:07:47.098Z using mcpSecurity-inventory. Status: succeeded. Negotiated protocol: 2025-06-18.
{
"tools": {},
"logging": {},
"completions": {}
}| Tool | Category | Annotations | Risk |
|---|---|---|---|
add_documentAdd a new document to the knowledge baseInput schema{
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "The title of the document"
},
"content": {
"type": "string",
"description": "The content of the document"
},
"metadata": {
"type": "object",
"properties": {},
"additionalProperties": false,
"description": "Optional metadata for the document"
}
},
"required": [
"title",
"content"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
delete_documentDelete a document from the collectionInput schema{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Document ID to delete"
}
},
"required": [
"id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
get_context_windowReturns a window of parent content sections around a central parent_index. Use parent_index values from search results. Always tell the user if result is truncated because of length.Input schema{
"type": "object",
"properties": {
"document_id": {
"type": "string",
"description": "The document ID"
},
"parent_index": {
"type": "number",
"description": "The parent_index of the central section (from search results)"
},
"before": {
"type": "number",
"default": 1,
"description": "Number of previous parent sections to include"
},
"after": {
"type": "number",
"default": 1,
"description": "Number of next parent sections to include"
}
},
"required": [
"document_id",
"parent_index"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
get_documentUse this tool only when user explicitly requests it. Retrieve a specific document by ID. Always tell the user if result is truncated because of length. for example if you recive a message like this in the response: 'Tool response was too long and was truncated'Input schema{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The document ID"
}
},
"required": [
"id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
get_ui_urlGet the URL of the web UI. use this tool when user ask you to access the web interface, when the user ask you to upload a file or when the user ask you the uploads folder path. All these function are available in the web UI.Input schema{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
get_uploads_pathGet the absolute path to the uploads folder where you can manually place .txt and .md filesInput schema{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
list_documentsList all documents in the knowledge baseInput schema{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
list_uploads_filesList all files in the uploads folder with their detailsInput schema{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
process_uploadsProcess all .txt and .md files in the uploads folder and create embeddings for themInput schema{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
search_all_documentsSearch for relevant chunks across ALL documents in the knowledge base using semantic similarity (hybrid: full-text + vector). Useful for cross-document search when you don't know which document contains the answer.Input schema{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The search query"
},
"limit": {
"type": "number",
"default": 10,
"description": "Maximum number of chunk results to return"
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |
search_documentsSearch for chunks within a specific document using semantic similarity. Always tell the user if result is truncated because of length. for example if you recive a message like this in the response: 'Tool response was too long and was truncated'Input schema{
"type": "object",
"properties": {
"document_id": {
"type": "string",
"description": "The ID of the document to search within"
},
"query": {
"type": "string",
"description": "The search query"
},
"limit": {
"type": "number",
"default": 10,
"description": "Maximum number of chunk results to return"
}
},
"required": [
"document_id",
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — · — | — |