Who it is for
Teams working against large document corpora such as regulatory or scanned archives.
AI Connectors · Data & Analytics
Document corpus parsing and search across 50-plus file types
Overview
POMA Grill is a managed context engine: files are added to it, parsed, and made searchable so a conversation can draw on a large document set without any of it being pasted in. Formats named include PDF, CSV, HTML and XLS with more than fifty others, plus URLs, and search extends into images and video across more than eighty languages. The listing points specifically at material that resists ordinary extraction, such as regulatory text and scanned PDFs, and at teams that want a private context layer rather than uploads. Nine tools are published, and a POMA account holding the corpus is required.
Teams working against large document corpora such as regulatory or scanned archives.
Nine tools cover adding files and searching them by the listing's account, but the endpoint returned a refusal with no reason given, so ingestion and retrieval calls cannot be separated here.
Availability
POMA Grill is listed in the Claude connectors directory only. POMA AI has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them.
The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one.
Claude listing
POMA Grill publishes 9 tools to Claude. That is a mid-sized surface: 41.3% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Data & Analytics publishes 12, so this one sits 3 tools below its bucket's median, 115th of 198.
It falls in the 7-10 tools band, which holds 14.6% of the Claude directory.
POMA Grill publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
https://mcp.poma-ai.com/v1 POMA Grill is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality.
In the publisher's words
POMA Grill is a managed context engine, letting you add files that can act as easily-searchable context for Claude. It can parse and search PDFs, CSVs, HTML, XLS, and 50+ more filetypes - even URLs! It also supports more than 80 languages, as well as searching within images and video. It's built for users and teams who have large document corpora that they want to use as a handy context layer when using Claude, while still maintaining privacy and security. It's great for anyone working with structured, complex documents, such as regulatory text or scanned PDFs.
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Web pages and documents converted to structured data
ChatGPT
Metadata catalog and lineage context for ChatGPT queries
ChatGPT
Render, publish, and manage chart images from structured data
Claude
Cloud and AI spend analysis across AWS, GCP, Azure, Snowflake and OpenAI
Claude
Enterprise data context: search, lineage, ownership and governance
Claude
Document sets turned into searchable structured facts
ChatGPT
This is an independent catalogue entry compiled by Node8 from POMA Grill's public marketplace listing as it stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with POMA AI, and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.