How to get the matching passages instead of reading whole files Leave feedback
On this page
An agent that reads whole documents to answer a question fills its context with text it does not need. With the GroupDocs.Search MCP server running locally, it calls get_text_fragments and gets only the passages that match, with as many words of context as you choose — so the answer cites the passage and the context stays small:
docker run --rm -i -v $(pwd)/documents:/data \
ghcr.io/groupdocs-search/search-net-mcp:latest
What do my contracts say about penalties? Quote the passages, with enough context to understand each one.
NoteThe commands and config snippets on this page are for the .NET build of the server, which ships as a Docker image only. Installation and client setup: MCP server for .NET. Other platforms will expose the same tools with their own launch command; everything else on this page applies unchanged.
- An index built with
add_to_index— see search documents with AI agents.
Reading the files Searching the index
------------------------------------- -------------------------------------
agent opens every document search: which files match (JSON)
context grows with the corpus get_text_fragments: the passages
long files crowd out the question (~8 words either side, per file)
repeated for every question answer cites file + passage
the index is reused next time
The index already holds the text, so the server can cut out the passage around each match. The agent never loads the rest of the file.
Captured from server 26.10.1. The defaults — 8 words either side — give a phrase:
-> get_text_fragments {"query":"penalty","indexName":"contracts"}
<- 3 document(s) match.
=== contracts/acme-master-services-agreement.pdf (1 occurrence(s)) ===
[content] …before the end of the Term, a termination penalty of
three monthly fees applies, payable within 30…
Twenty words either side give the clause:
-> get_text_fragments {"query":"penalty","indexName":"contracts",
"termsBefore":20,"termsAfter":20,"maxFragmentsPerDocument":1}
<- === contracts/acme-master-services-agreement.pdf (1 occurrence(s)) ===
[content] …convenience on 90 days written notice.
12.3 If the Client terminates before the end of the Term, a termination
penalty of three monthly fees applies, payable within 30 days of the
termination date.
14.2 Force majeure: neither party is…
| Parameter | Default | Raise it when |
|---|---|---|
termsBefore / termsAfter | 8 | you need the whole clause or sentence |
maxFragmentsPerDocument | 3 | a word occurs many times and you want every use |
maxDocuments | 5 | the answer spans more files |
Full-text search matches words, so let the agent try the variants:
-> search {"query":"renewal OR renews","indexName":"contracts"}
<- umbrella-office-lease.pdf — terms ["renewal", "renews"]
-> search {"query":"renewl","indexName":"contracts","fuzzy":true}
<- umbrella-office-lease.pdf — terms ["renewal", "renews", "rent"]
Fuzzy matching also found rent: check the terms a fuzzy search reports before trusting it.
Each answer arrives with the file and the quoted passage it rests on. When the quote does not support the answer, you can see it — which is the point.
| Symptom | Cause | Fix |
|---|---|---|
| A fragment starts mid-sentence | context is counted in words, not sentences | raise termsBefore |
| "(no stored text for this document…)" | the document was indexed without stored text | re-add it with add_to_index |
| A fragment contains “Evaluation only. Created with GroupDocs.Parser…” | evaluation mode adds this line to the text of some formats | license the server, then rebuild the index |
How much context does this save? It depends on the corpus; the fragments for one question are a few hundred words, against the full text of every candidate file. The bigger the files, the bigger the difference.
Can the agent still read a whole file? Yes, with its own file tools. Fragments are for finding and quoting; read the whole file when the passage is not enough.
Are the fragments exact? They are the indexed text, with … marking where the window was cut. Line breaks follow the document.
Agents follow project instructions about when to use a tool. Paste this into the instruction file your agent reads (CLAUDE.md, AGENTS.md, .github/copilot-instructions.md, .cursorrules):
Answer questions about documents in ./documents from passages, not whole files:
get_text_fragments (raise termsBefore/termsAfter for full clauses), quote the
passage and its file. Try OR-lists or fuzzy=true when a query finds nothing.
- Evaluation mode: an index holds at most 100 documents and a search returns at most 10 — the response says so in its
evaluationfield. Licensing. - Full-text, not semantic: it matches words, not meaning. Ask the agent to try variants (
OR,fuzzy: true). - No OCR: scans without a text layer are indexed by their file properties only.
- Docker only: there is no
dnxchannel for this product (why).
- Search documents with AI agents
- Search a folder of contracts
- Keep an index up to date
- Search documents in a code repository
- Search email archives
- Find documents by date and amount
- On-premise deployment
- Tools reference · Licensing · Troubleshooting & FAQ
- Questions: Search forum
- Grounded answers from your files: quote the passage, not the model’s memory — the same scenario on the GroupDocs blog, with worked examples and the trade-offs.
Was this page helpful?
Any additional feedback you'd like to share with us?
Please tell us how we can improve this page.
Thank you for your feedback!
We value your opinion. Your feedback will help us improve our documentation.
