Endpoints: 28,729MCP servers: 18,413Payout addresses: 2,071Paid calls: 1,552Letters: 14Defects: 1,331counted 4 min ago
teppi

Server definition

Hash
sha256:c59f7836dce5769066a7a58cc8c2169c52bfcaa8e212b53ab87db5132bb2f909
What it is
What a remote MCP server returned when asked what it offers: 3 tools

The blob, as servednamed by its sha256

{ "instructions": null, "tools": [ { "description": "Convert a document up to 8 MB to Markdown and return it directly.\n\nPass the file as base64 in `content_base64`, or as a download link in\n`file`, and its name in `filename`. The extension decides the type: .pdf,\n.docx, .pptx, .xlsx, .html, .htm or .txt. Returns `markdown` and `meta`\n(`filename`, `length` in characters). PDFs come back as plain text\nwithout headings and without OCR. For scans, tables and page numbers,\nuse `submit_conversion_job`. Works without an API key at the anonymous\nrate limit.\n\nCredits: 1 per call.", "inputSchema": { "additionalProperties": false, "properties": { "content_base64": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The file content, base64-encoded. Up to 8 MB before encoding." }, "file": { "default": null, "description": "The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL.", "properties": { "download_url": { "description": "A public https URL of the file.", "type": "string" }, "file_id": { "description": "An identifier for the file. ChatGPT sets it; other clients may pass any label, such as the file name.", "type": "string" }, "file_name": { "type": "string" }, "mime_type": { "type": "string" } }, "required": [ "download_url", "file_id" ], "type": "object" }, "filename": { "description": "The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read.", "type": "string" } }, "required": [ "filename" ], "type": "object" }, "name": "convert_document", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Check a queued conversion job you submitted.\n\nReturns `job_id` and `status` (`queued`, `running`, `succeeded` or\n`failed`). A succeeded job includes the `markdown` when it is under\n100 KB, otherwise a `result_url` to download it (also free). A failed job\nincludes `error`, one sentence with the reason. Results are deleted\n7 days after submission. An expired result is reported in `error`.\nRequires an API key.\n\nCredits: free. This tool is not metered.", "inputSchema": { "additionalProperties": false, "properties": { "job_id": { "description": "The `job_id` returned by `submit_conversion_job`.", "type": "string" } }, "required": [ "job_id" ], "type": "object" }, "name": "get_conversion_job", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Queue a document up to 25 MB and 200 pages for conversion with OCR and tables.\n\nPass the file as base64 in `content_base64`, or as a download link in\n`file`, and its name in `filename` (.pdf, .docx, .pptx, .xlsx, .html,\n.htm or .txt). Returns `job_id`, `status` and `result_url`. Call\n`get_conversion_job` with the `job_id` until `status` is `succeeded` or\n`failed`. A conversion may take up to about 2 minutes.\n\nOptional `webhook_url`: a public http or https URL that receives a POST\nwith the job's final state. The request carries\n`X-Appkit-Signature: sha256=<hex>`, an HMAC-SHA256 of the raw body keyed\nwith the returned `webhook_secret` (shown only once). 3 delivery attempts.\n\nRequires an API key. The credits are refunded if the job fails. The\nuploaded file is deleted when the job finishes. Results are kept for\n7 days after submission.\n\nCredits: 10 per call.", "inputSchema": { "additionalProperties": false, "properties": { "content_base64": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The file content, base64-encoded. Up to 25 MB before encoding." }, "file": { "default": null, "description": "The file as a download link, instead of `content_base64`. In ChatGPT, pass the user's uploaded file here. Other clients can set `download_url` to a public https URL.", "properties": { "download_url": { "description": "A public https URL of the file.", "type": "string" }, "file_id": { "description": "An identifier for the file. ChatGPT sets it; other clients may pass any label, such as the file name.", "type": "string" }, "file_name": { "type": "string" }, "mime_type": { "type": "string" } }, "required": [ "download_url", "file_id" ], "type": "object" }, "filename": { "description": "The file name with its extension (.pdf, .docx, .pptx, .xlsx, .html, .htm or .txt). The extension decides how the file is read.", "type": "string" }, "webhook_url": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Optional. A public http or https URL that receives the job's final state." } }, "required": [ "filename" ], "type": "object" }, "name": "submit_conversion_job", "outputSchema": { "additionalProperties": true, "type": "object" } } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:c59f7836dce5769066a7a58cc8c2169c52bfcaa8e212b53ab87db5132bb2f909 | sha256sum