MCP server for searching documentation, scanning dependencies for vulnerabilities, and generating project boilerplate. Works with Claude Desktop
Documentation Search MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP server for searching documentation, scanning dependencies for vulnerabilities, and generating project boilerplate. Works with Claude Desktop, Cursor, and other.
Installation goes through your MCP client rather than a global install: point it at documentation-search-enhanced on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once Documentation Search MCP is connected, these are the calls the assistant has available:
semantic_search — Search documentationget_docs — Fetch specific documentationget_learning_path — Generate learning roadmapget_code_examples — Find code snippetsscan_project_dependencies — Vulnerability scansnyk_scan_project — Detailed Snyk analysisgenerate_project_starter — Create project boilerplatemanage_dev_environment — Generate docker-compose filescompare_library_security — Compare library vulnerabilitiesTesting — The Testing tool exposed by this serverConfiguration — Use the get_current_config tool to export current settings to config.json. Validate with: bash uv run pythonYou will need 2 environment variables: SERPER_API_KEY, DOCS_SITE_INDEX_PATH. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Documentation Search MCP's toolset — semantic_search, get_docs, get_learning_path and 8 more — is a fair guide to whether it matches your workflow. It is maintained by anton-prosterity; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Documentation Search MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| semantic_search | Search documentation |
| get_docs | Fetch specific documentation |
| get_learning_path | Generate learning roadmap |
| get_code_examples | Find code snippets |
| scan_project_dependencies | Vulnerability scan |
| snyk_scan_project | Detailed Snyk analysis |
| generate_project_starter | Create project boilerplate |
| manage_dev_environment | Generate docker-compose files |
| compare_library_security | Compare library vulnerabilities |
| Testing | The Testing tool exposed by this server. |
| Configuration | Use the get_current_config tool to export current settings to config.json. Validate with: bash uv run python src/documentation_search_enhanced/config_validator.py |
{
"mcpServers": {
"documentation-search": {
"command": "uvx",
"args": ["documentation-search-enhanced"],
"env": {
"SERPER_API_KEY": "your-value",
"DOCS_SITE_INDEX_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| SERPER_API_KEY | Credential the server authenticates with. | Yes |
| DOCS_SITE_INDEX_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.