MCP & Integrations
Limma
Last updated 2026-10-27 · benchmark measured 2026-10-27 — deterministic & reproducible
Limma is an MCP server that indexes company documents and data for AI agent queries.
Limma at a glance
Limma is an MCP server that reads a company's documents, spreadsheets, emails, and business systems once and returns complete, sourced answers to AI agent queries, built for teams and enterprises that need full-coverage results rather than similarity-ranked fragments.
Good for
- AI agents that need complete, countable answer sets instead of a handful of similarity-ranked fragments
- Document-heavy organizations connecting many sources (documents, spreadsheets, email, cloud folders, business systems) that need one query endpoint
- Teams or enterprises that need every returned value traced back to its exact source document, page, and words for verification
Pricing
Free: 250 pages/mo. Starter $49/mo (2,500 pages). Team $199/mo (12,000 pages). Business $799/mo (60,000 pages). On-prem: custom licence, unmetered.
Questions people ask
What does Limma actually do?
It reads all the documents and data sources a company connects, builds a structured map of their contents, and answers AI agent queries through a single MCP endpoint with a complete, sourced result set rather than a sample of ranked fragments.
What kinds of documents and data can Limma connect to?
Files and folders (PDF, scanned PDF, Word, Excel, PowerPoint, email, CSV, JSON, HTML, Markdown), cloud storage (Amazon S3, Azure Blob Storage, Google Cloud Storage), Google Drive and SharePoint/OneDrive for Business, and databases such as PostgreSQL, MySQL and SQLite, plus CSV/Excel/JSON exports. Native connectors for Notion, Slack, Confluence, Gmail and Outlook are coming next.
How is Limma priced?
Pricing is based on pages processed per month: Free (250 pages), Starter $49/month (2,500 pages), Team $199/month (12,000 pages), Business $799/month (60,000 pages), and a custom on-premises licence with unmetered pages. A request that would exceed a plan's limit is refused rather than billed as an overage.
What happens to our data when using Limma?
Documents are read by an AI model running on Limma's own servers, are never sent to OpenAI or Anthropic, and are never used to train any model; deleting a document also deletes everything taken from it. Limma can also run entirely inside a company's own network via the on-premises option.
Can I see where an answer came from?
Yes, every value Limma returns links back to the specific document, page, and exact words it came from, and if two documents conflict or a document cannot be read, Limma reports that instead of guessing.
Written by Legit.Show from limma.ai on 2026-10-31. It does not change the score.
Are you the maker of Limma? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/limma-ai/2026-10-27. That address never changes; this page moves with every re-measure.
Legit.Show scored Limma 82/100 on 2026-10-27, measured across all 7 frames from its public surface. legit.show/s/limma-ai/2026-10-27
Is Limma production-ready?
Legit.Show scores Limma 82 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Limma (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 63/100
- Accessibility — 96/100
- Security — 25/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 100/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 73 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who it's for
AI agents · Teams using AI · Enterprises with multiple data sources · Document-heavy organizations
Pricing
Free (250 pages/month), Starter $49/month (2,500 pages), Team $199/month (12,000 pages), Business $799/month (60,000 pages), On-prem custom
Sources and updates
- Description
- Taken from limma.ai's own website on 2026-10-27.
- Operator
- Limma, as named in limma.ai's terms, privacy page or footer.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-10-27.
Put together from public information, without Limma's involvement. If anything here is wrong, tell us and a person will check it.
Visit Limma → · Alternatives to Limma → · How this was measured →