knowledge-cache
MCP server for caching technical documentation, API references, and code patterns in SQLite + FTS5. Reduces repeated web lookups by storing knowledge locally with tag-based categorization and full-text search.
How it works
Agent -> knowledge_find("navmesh setdestination", ["unity"])
├── hit → returns cached content (avoids web fetch)
└── miss → fetch via context7 → knowledge_store(content, tags, url)
Tools
| Tool | Args | Description |
|---|---|---|
knowledge_find |
query: str, tags?: str[], limit?: int |
FTS5 full-text search with optional tag filter |
knowledge_store |
content: str, tags: str[], source_url?: str |
Store and index a knowledge entry |
knowledge_stats |
— | Cache statistics: total entries, top tags, date range |
knowledge_forget |
id: int |
Remove a stale entry |
Storage
SQLite with FTS5 for full-text search. Schema:
knowledge— entries with content, source URL, timestampsknowledge_fts— FTS5 virtual table (porter stemmer, prefix matching)knowledge_tags— category tags per entry (NOCASE, multi-tag filter)
Default database path: ./.knowledge/knowledge.db (configurable via --db-path).
Setup
Install
cd knowledge-cache
uv add mcp
MCP config (per project .mcp.json)
{
"mcpServers": {
"knowledge-cache": {
"command": "uv",
"args": [
"run",
"--directory", "/path/to/knowledge-cache",
"server.py",
"--db-path", "/path/to/project/.knowledge/knowledge.db"
]
}
}
}
Dependencies
Zero (stdlib: sqlite3, os, argparse). Requires mcp package for the MCP server transport. FTS5 is built into Python's SQLite on Windows.
Metadata
Release files for knowledge-cache 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| knowledge_cache-0.1.0.tar.gz | 41.6 kB | Without provenance | Details for knowledge_cache-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| knowledge_cache-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for knowledge_cache-0.1.0-py3-none-any.whl |
Total release size: 87.8 kB
Release files / knowledge_cache-0.1.0.tar.gz
| Download URL | knowledge_cache-0.1.0.tar.gz |
|---|---|
| Size | 41.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3596ffc5aa36e50142f144ec2e69894379c3d954dc803745c60e787fd8449554
|
|
BLAKE2b-256 checksum How to use checksums |
2db944209f8a9332352217e08c03dab540891d20389e03a2905c843411b4582a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.12
|
Release files / knowledge_cache-0.1.0-py3-none-any.whl
| Download URL | knowledge_cache-0.1.0-py3-none-any.whl |
|---|---|
| Size | 46.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
49c3f67564a8c6d2f3f5df6d66073d120d06fdb7dd6918700804985cc449dc0d
|
|
BLAKE2b-256 checksum How to use checksums |
441d24f5bc1497b2cbc1ca81d9e155030cf28cafd61b1337890ce96d111d6391
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.7.12
|
Security for knowledge-cache 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.