
Olaverse Lab
Document extraction with calibrated confidence, decisions, language ID in 608 languages, diacritics.
- tools
- 6
- auth
- Secret needed
- transport
- STDIO, HTTP
- env var
- 1
- last updated
- Nov 6, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
extract_documentA document (text, a JPEG/PNG photo or scan, or a PDF) to JSON shaped like your template, with a calibrated confidence for every field.
A document (text, a JPEG/PNG photo or scan, or a PDF) to JSON shaped like your template, with a calibrated confidence for every field.
No parameter schema in public metadata yet.
get_extraction_jobCollects a long-document result that's still running.
Collects a long-document result that's still running.
No parameter schema in public metadata yet.
decideTyped questions about a message, ticket or record (yes/no, choice, score), with calibrated probabilities.
Typed questions about a message, ticket or record (yes/no, choice, score), with calibrated probabilities.
No parameter schema in public metadata yet.
detect_languageThe language of a text, among 608 (built African-first, good on very short text).
The language of a text, among 608 (built African-first, good on very short text).
No parameter schema in public metadata yet.
restore_diacriticsPuts back tone marks, accents and Arabic vowel marks in 11 languages, including Yorùbá, Igbo, Hausa and Arabic.
Puts back tone marks, accents and Arabic vowel marks in 11 languages, including Yorùbá, Igbo, Hausa and Arabic.
No parameter schema in public metadata yet.
generate_questionsSearch-style questions a passage answers, in the passage's own language (25 languages).
Search-style questions a passage answers, in the passage's own language (25 languages).
No parameter schema in public metadata yet.
Sponsors
Configuration
OLAVERSE_API_KEY*secretYour Olaverse API key (console.olaverselab.com)
Readme
Olaverse MCP server
Olaverse Lab's API as tools for AI agents: Claude, Cursor and any other MCP client. The models are small, task-specific and strongest on English and African-language text.
| Tool | What it does |
|---|---|
extract_document | A document (text, a JPEG/PNG photo or scan, or a PDF) to JSON shaped like your template, with a calibrated confidence for every field. Long documents are split, extracted in parallel and merged. |
get_extraction_job | Collects a long-document result that's still running. |
decide | Typed questions about a message, ticket or record (yes/no, choice, score), with calibrated probabilities. 19 languages. |
detect_language | The language of a text, among 608 (built African-first, good on very short text). |
restore_diacritics | Puts back tone marks, accents and Arabic vowel marks in 11 languages, including Yorùbá, Igbo, Hausa and Arabic. |
generate_questions | Search-style questions a passage answers, in the passage's own language (25 languages). |
Set up
Details
- Repository
- github.com/olaverse-labs/olaverse-mcp
- Website
- www.olaverselab.com
- Category
- Documents & Knowledge
- Package
olaverse-mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active