Metadata-Version: 2.4
Name: opensolr-mcp
Version: 0.8.1
Summary: MCP server for Opensolr — managed Apache Solr with hybrid BM25+kNN search, server-side embeddings, and RAG answers as agent tools
Author-email: Opensolr <support@opensolr.com>
License: MIT
Project-URL: Homepage, https://opensolr.com/mcp
Project-URL: Repository, https://github.com/phpcip/opensolr-mcp
Keywords: mcp,model-context-protocol,opensolr,solr,hybrid-search,rag,agents,vector
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: mcp>=1.2.0
Requires-Dist: httpx>=0.25.0
Dynamic: license-file

# opensolr-mcp

mcp-name: com.opensolr/opensolr-mcp

MCP (Model Context Protocol) server for [Opensolr](https://opensolr.com) —
gives any AI agent **managed Apache Solr search** as tools: hybrid
(BM25 + kNN) retrieval, server-side GPU embeddings, document indexing (local
files and folders too, PDFs page by page, scans through OCR), and grounded RAG
answers.

**See it live (real news index, hybrid + AI answer):** https://search.opensolr.com/news__dense?q=how+am+I+supposed+to+save+money%3F

No embedding model to configure. No vector database to run. One API key.

## Tools

| Tool | What it does |
|---|---|
| `opensolr_search` | Hybrid (keyword + semantic) or pure semantic search, with Solr filters and a date range; a PDF comes back as its best page, with a link that opens it at that page |
| `opensolr_search_by_image` | Search with a **photo** — Opensolr reads its visual labels, OCR text and any barcode/QR, then searches with those words (no image vector stored) |
| `opensolr_read_document` | Read one result in full — a PDF page by page, any other document as one text |
| `opensolr_ai_answer` | Grounded RAG answer: top hybrid hits become the LLM context — same pipeline as the hosted search UI |
| `opensolr_index_files` | Index a local file or a whole folder: PDFs one document per page, Word / RTF / OpenDocument / text / HTML, scans and pictures through OCR |
| `opensolr_extract_text` | Read local files without indexing them: text, OCR of their pictures, a PDF page by page |
| `opensolr_describe_image` | What a picture shows (a sentence), the text printed on it, its labels and barcodes |
| `opensolr_add_documents` | Index plain text + metadata (embedded server-side) |
| `opensolr_delete_documents` | Remove documents by id |
| `opensolr_list_indexes` / `opensolr_index_info` | Inspect the account's indexes |
| `opensolr_create_index` | Provision a vector index in a region of `opensolr_vector_regions` (an environment id, or a short form like `us` matched against that live list) |
| `opensolr_vector_regions` | Live list of vector-enabled regions |
| `opensolr_check_schema` | Whether an index can do what each tool needs (Data Ingestion, vector and hybrid search, PDF pages, keyword search), and exactly why not |
| `opensolr_apply_schema` | Install the Opensolr vector schema on an index of a vector region (replaces its configuration; `force` when it holds documents) |

## Setup

Get a free Opensolr account (free forever, no card) at
[opensolr.com/register](https://opensolr.com/register) and copy your API key
from **Account**.

### Try it without an account

There is a public demo account. Point the package at it and everything in this
README works immediately, with no signup:

```bash
export OPENSOLR_EMAIL=mcp@opensolr.com
export OPENSOLR_API_KEY=420b8b23e7b12dc8ab838932145a5065
```

`mcp_demo_d1__dense` is already loaded with 300 news articles, so search, filtering
and grounded answers work the moment you connect. You also get the write path:
create your own index on the account, ingest into it and query it. Deletion is not
available on this shared key: no index here can be deleted or reconfigured by hand.
Whatever you create is removed automatically after 3 days.

Know what you are working with:

- **Anything you create there is deleted after 3 days.** Automatically, without warning
  or export. That includes indexes you created and every document in them.
- **The account is shared with everyone reading this.** Your index is visible to them
  and they can add documents to it, as you can to theirs. Nobody can delete or
  reconfigure an index here (that is switched off for this key), but never put anything
  real, private or client-owned in it.
- **The limits are per index, and deliberately small.** 200 MB of bandwidth and 50 MB
  of disk per index. Bandwidth is the one you will hit first: it covers a demo, a
  tutorial and a proof of concept, and it will not carry an application.

When you want an index that is private, yours and still there next week, get your own
key — [free forever, no card](https://opensolr.com/register) — and change the two
variables above. Nothing else in your code changes.

### Claude Desktop / Claude Code

```json
{
  "mcpServers": {
    "opensolr": {
      "command": "uvx",
      "args": ["opensolr-mcp"],
      "env": {
        "OPENSOLR_EMAIL": "you@example.com",
        "OPENSOLR_API_KEY": "YOUR_OPENSOLR_API_KEY"
      }
    }
  }
}
```

### Cursor / Windsurf / any MCP client

Same shape — stdio transport, command `uvx opensolr-mcp` (or
`pipx run opensolr-mcp`), with `OPENSOLR_EMAIL` and `OPENSOLR_API_KEY` in env.

## Example agent session

> **You:** Index our FAQ answers, then find everything about refunds.
>
> The agent calls `opensolr_add_documents(index="faq__dense", texts=[...])`,
> then `opensolr_search(index="faq__dense", query="refund policy", hybrid=True)`
> — BM25 catches the exact word "refund", kNN catches "giving customers their
> money back", and the scores fuse per document.

## Search with a photo

`opensolr_search_by_image` lets the agent search with a **picture** instead of a
text query. Opensolr reads the image three ways — visual labels (what it
depicts), OCR text (words printed on it), and any barcode / QR code — turns that
into words, and runs the normal search. No image vector is stored.

```
opensolr_search_by_image(index="catalog__dense", image_path="/tmp/shelf.jpg",
                         using="auto", k=5)
# using: "auto" (engine's choice) | "meaning" (visual labels) |
#        "text" (OCR only) | "code" (exact barcode/QR) | "all" (everything)
# -> { "read": {text, mode, labels, codes}, "results": [...] }
```

`search_mode`, `mode`, `alpha`, `fresh_bias`, `filter_query`, `date_from`, `date_to`
and `group_pages` behave exactly as in `opensolr_search`.

## Local files and folders: PDFs page by page, scans through OCR

`opensolr_index_files` indexes a file or a whole folder from the machine the server
runs on. Each file is read on Opensolr's servers — its text, the text in its
pictures (OCR, more than 100 languages), a short description of the pictures that
have no text — and a **PDF is indexed one document per page**, so a search lands on
the page that answers it instead of a 200-page file that mentions it somewhere.
Word, RTF, OpenDocument, text, HTML and picture files (scans, photos of documents)
are one document each.

```
opensolr_index_files(index="contracts__dense", path="~/Documents/contracts",
                     pattern="*.pdf", metadata={"team": "legal"})
# -> {"documents": [{path, source, uri, id}], "pending": [], "failed": [], "jobs": [...]}
```

- The bytes travel once: a file the account already sent (same content) is not
  uploaded again, and sending the same files again replaces their documents.
- Each document's `uri` is `https://ingest.opensolr.com/<index>/<source>`, where
  `source` is the file's path from the folder you sent (also in `meta_source`); its
  date is the file's modification time, so date ranges work on local files too.
- Big files are read in the background: whatever is still being read after
  `wait_seconds` comes back under `pending`; call the tool again with the same path
  to index those (nothing is sent twice).
- Pictures read by OCR count 0.5 of an AI request each; a file read before is free.

`opensolr_extract_text` does the same reading without indexing anything — the text of
each file, a PDF as its pages (`page`, `text`, `is_ocr`, `lang`) — for an agent that
wants to read a contract, a scanned invoice or a folder of reports itself.

`opensolr_describe_image` answers what a picture shows and what is written on it:
`caption` (a sentence), `text` (OCR), `labels` and barcode / QR `codes`.

## PDF pages in search results

On an index where PDFs are stored page by page (files indexed above, PDFs sent to
Data Ingestion with `rtf`, PDFs found by the Web Crawler), `opensolr_search` returns
each PDF **once**, as its best page:

```
{"title": "Master services agreement", "page": 14,
 "page_url": "https://example.com/msa.pdf#page=14",   # opens the PDF at that page
 "document_id": "9f2c...",                            # for opensolr_read_document
 "more_pages": [{"page": 3, "page_url": "...#page=3"}, ...],  # its other matching pages
 "matching_pages": 4, "uri": "https://example.com/msa.pdf", ...}
```

`group_pages=false` returns the pages as separate results. `opensolr_read_document`
reads any result in full: a PDF as its pages in order (`page_from` / `page_to`), any
other document as one text.

## Searching a period

`date_from` and `date_to` (`YYYY-MM-DD`, both included, either one can be left out)
keep only the documents dated in that period (`creation_date`). They combine with
every other option, `fresh_bias` included.

## Search operators

The query string understands the operators people already expect from a search box. They work
in every mode — keyword, hybrid and pure vector.

| Operator | Meaning | Example |
| --- | --- | --- |
| `"word1 word2"` | Phrase — those words together, in that order | `"machine learning"` |
| `+word` | Required — every result must contain it | `+laptop 15 inch gaming` |
| `+"word1 word2"` | Required phrase | `+"13 inch"` |
| `-word` | Excluded — drop any document containing it | `laptop -refurbished` |
| `-"word1 word2"` | Excluded phrase | `-"open box"` |

They compose: `+laptop +"13 inch" -refurbished` returns only 13-inch laptops and never a
refurbished one.

A prefixed term (`+` or `-`, word or phrase) becomes a **filter**, applied to the whole result
set. That matters as soon as a vector is involved: the semantic side of a hybrid search has no
concept of negation, so left as query text `-refurbished` would actually pull refurbished
listings *towards* the top rather than removing them. As a filter it binds every document,
whichever side of the search found it, and the exclusion is absolute.

An unprefixed phrase (`"machine learning"` with no `+` in front) is a keyword-side relevance
signal rather than a filter — use `+"machine learning"` when you need it enforced.

`+` and `-` only count at the start of a word, so `e-mail`, `covid-19` and `1+1` are searched
for literally.

## Notes

- Vector indexes live in the **vector regions**: the Opensolr servers that run the
  web crawler, whatever their Solr version. The list is live, never written in the
  package: `opensolr_vector_regions` returns the regions that take new indexes right now
  (environment id, country, Solr version). `location=` takes an environment id from
  that list, or a short form such as `us`, `de` or `fi`, matched against the live
  list by environment id or country. **Additional dedicated regions can be deployed
  on request** (paid add-on): [support@opensolr.com](mailto:support@opensolr.com).
- Every index is also plain Apache Solr with the native `/select` API —
  nothing is locked behind the tools.
- Python sibling for LangChain: [`langchain-opensolr`](https://pypi.org/project/langchain-opensolr/) ·
  Product page: [opensolr.com/langchain](https://opensolr.com/langchain)

## How writing works (Data Ingestion API)

Writes go through Opensolr's [Data Ingestion API](https://opensolr.com/learn/api-data-ingestion/204/data-ingestion-api-push-documents-to-your-opensolr-index-programmatically)
— the same pipeline the Drupal and WordPress connectors use. It is
**asynchronous**: documents are queued, then embeddings, sentiment, language
and all crawler-identical derived fields are computed **server-side**, and
documents become searchable within about a minute. Progress is visible in
**Control Panel → Data Ingestion** — a per-job status board (queued /
processing / completed / failed, with processed / success / failed document
counts per job) — and via the `ingest_status` API. Each document's
identity is its `uri` (the Solr id is `md5(uri)`): pass a real URL in
metadata (`{"uri": "https://..."}`), or a deterministic one is synthesized
from your id. Re-submitting the same `uri` updates the document. Pass
`{"rtf": True, "uri": "https://.../file.pdf"}` and the server extracts the
text from PDF/DOCX/XLSX for you.

## Lexical-only mode

Don't need vectors? Pure keyword search skips the embedding call entirely —
zero AI quota. It runs on any Opensolr index that has `title`, `description` and
`text` fields, including indexes outside the vector regions and older Solr
versions (see [Index requirements](#index-requirements)).

## Index requirements

Everything this package does runs on an Opensolr index that sits in a **vector
region** and carries the **Opensolr vector schema** — the configuration every
Opensolr vector index runs. An index created through the package (`create_index`,
`create_if_missing`) has both. An index made elsewhere may not: a server outside
the vector regions, or a schema of its own. A vector region is an Opensolr server
that runs the web crawler, whatever its Solr version; the regions that take new
indexes come from the live `vector_regions` list, never from a list in the package.

**The check is automatic.** The first time the package touches an index, it asks
the platform once whether that index can do what is asked: one request per index
per client, kept for the client's life, never one per search. If the check itself
cannot run (a network error, the platform busy), nothing is blocked: the
operation runs exactly as it always did, and the check is tried again after 5
minutes. When an index differs from the Opensolr vector schema, a warning is logged
once, on the `opensolr` logger, with the reasons and the fix.

What the check gates — only what cannot work otherwise:

| Capability | Needed for | When it is missing |
|---|---|---|
| `ingestion` | Data Ingestion: adding documents and indexing files | The index is outside the vector regions: refused before a document or a byte is sent |
| `vector_search` | Vector and hybrid search | The index has no vector field of the right size: refused before any embedding is paid for |
| `pdf_pages` | Grouping the pages of a PDF in search results | Results come back ungrouped, as before |
| `keyword_search` | Keyword (lexical) search | Never blocked |

**The errors say exactly what is going on.** A blocked operation raises
`OpensolrSchemaError` (a subclass of `OpensolrError`) with `.index`, `.capability`
and `.report` (the full check), and a message with every reason and the fix:

```
Index 'shop_it' cannot take documents or files through Data Ingestion. Index shop_it
is on IT-SOLR-9-6 (Milano, Italy), which is not a vector region: Data Ingestion,
server-side embeddings and hybrid search run only on the servers of a vector region
(DE-SOLR-9 (Germany, Solr 9.00), FINLAND9 (Finland, Solr 9.60), ...). This index
cannot be made ready: create a new index in one of the vector regions (...), for
example with create_index, and send your documents there.
```

When Solr itself refuses a request, `OpensolrSolrError` carries Solr's own reason
and the index name; it is still an `httpx.HTTPStatusError`, so code that caught
that before keeps working.

```python
from opensolr_mcp.client import OpensolrClient, OpensolrSchemaError

client = OpensolrClient(email, api_key)
try:
    client.ingest_files("shop_it", "~/Documents/catalog")
except OpensolrSchemaError as e:
    print(e.capability, e.report["fix"]["action"])   # ingestion new_index
```

**See the details, and fix what can be fixed:**

```python
client.check_schema("shop_it")   # ready, capabilities, server, Solr version, missing / different fields, problems, fix
client.apply_schema("shop_it", force=False)   # installs the Opensolr vector schema; force=True when the index holds documents
```

`apply_schema` exists so an index of a vector region whose configuration was
changed, or never set, can take everything this package does without being
recreated: it installs the same configuration every Opensolr vector index runs,
and **replaces the index configuration**. An index that already holds documents
needs `force=True`; those documents keep the fields they were written with and
must be sent again. An index outside the vector regions cannot take it — create
a new index in a region from `vector_regions` and send your documents there. The
package never installs the schema on its own.

In an agent, the same two calls are the tools `opensolr_check_schema` and
`opensolr_apply_schema`; every other tool runs the check on its own and returns
the message above when it refuses.


## Your index schema

Documents follow the Opensolr document model (`title`, `description`, `text`,
`meta_*` custom fields). The whole schema, every field and every type suffix,
is explained in the [Index Schema Reference](https://opensolr.com/opensolr-platform-user-documentation/schema-reference).
To see your own copy: **Control Panel → click your
index → Configuration → Edit File → schema.xml**. Prefer zero-effort data
entry? Configure the **Web Crawler** in the Control Panel (Index Tools →
WebCrawler): add your site URL, validate it, and Opensolr indexes the whole
site for you.


### Search tuning

Retrieval (search and RAG grounding) runs through the platform's tuned
pipeline: global defaults → your index's saved **Search Tuning** (Control
Panel → Index Settings → Search Tuning: semantic↔lexical balance, field
weights, minimum match, search mode, vector candidate pool, content quality
boost) → optional per-call overrides via `tuning`:

```
tuning={"search_mode": "keywords_required", "fw_title": 0.2,
        "mm": "strict", "vector_topk": 500, "quality_boost": 0.3}
```

Defaults match the platform's PHP configuration exactly — customize in the
Control Panel once, or per call from code.

#### Fresh Results Bias

Rank newer documents higher without hiding anything older. Every score is
multiplied by a recency curve on `creation_date` — full weight for a document
published today, about half after a year:

```python
store.similarity_search_with_score("solar inverter warranty", fresh_bias=True)
client.hybrid_search(index, query, fresh_bias=True)
client.ai_answer(index, question, tuning={"fresh_bias": 1})
```

It **re-orders and never filters**: the hit count is identical either way,
nothing old becomes unreachable, and a document with no `creation_date` simply
keeps its place instead of being pushed to the bottom. It applies to all three
retrieval shapes — vector-only, keyword-only and the fused hybrid ranking —
because the boost wraps the final score rather than one half of it. Off by
default.

This is the same control visitors get as the **Fresh** toggle beside the sort
options on the hosted Opensolr search page, so a query behaves identically here
and there.

> `fresh_bias` and `freshness_boost` are two different knobs and the names
> invite confusion. `freshness_boost` is a hard window in **days** — anything
> older is filtered out and the hit count drops. `fresh_bias` filters nothing.

## How it's tested

Every release is validated against **live Opensolr infrastructure** — no mocks:

- **Unit tests** (offline): location matching against the live region list, filter→fq mapping, query building, escaping.
- **End-to-end suite**: the full write path through the async Data Ingestion
  queue (queued → server-side enrichment → searchable), semantic / hybrid /
  lexical retrieval, metadata round-trip, filters, id round-trip (your ids
  and the Solr `md5(uri)` ids), deletes by id and by query.
- **Real-corpus validation**: searches run against a 340-document replica of
  opensolr.com's own production search index. Verified: pure-semantic hits
  with zero keyword overlap ("how do I get my data back after a disaster" →
  backup &amp; restore docs), cross-lingual queries (Romanian query → English
  content), exact-term surfacing in hybrid mode, all four hybrid modes, and
  the full alpha range 0 → 1.
- **PDF ingestion**: a real PDF ingested via `rtf:true` — server-side text
  extraction (13k+ chars), automatic content-type detection, then retrieved
  with a purely semantic query against its contents.

The tools are exercised live (search modes, ingestion with wait, status,
deletes, RAG answers) before every release. RAG grounding is verified
end-to-end: a question answerable only from the ingested PDF returns the
correct answer sourced from the PDF's extracted text.

MIT license.
