Search / io.github.IvanRublev/keyphrases-mcp
keyphrases-mcp
L0· runs locallyAn MCP server to extract keyphrases from a text with the BERT model
v0.0.4 · active · repository · descriptor JSON · versions
Search / io.github.IvanRublev/keyphrases-mcp
L0· runs locallyAn MCP server to extract keyphrases from a text with the BERT model
v0.0.4 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"keyphrases-mcp": {
"command": "uvx",
"args": [
"keyphrases-mcp-server",
"--allowed-dir",
"keyphrases-mcp==0.0.4"
]
}
}
}claude mcp add keyphrases-mcp -- uvx keyphrases-mcp-server --allowed-dir keyphrases-mcp==0.0.4[mcp_servers.keyphrases-mcp]
command = "uvx"
args = ["keyphrases-mcp-server", "--allowed-dir", "keyphrases-mcp==0.0.4"]
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"keyphrases-mcp": {
"type": "local",
"command": [
"uvx",
"keyphrases-mcp-server",
"--allowed-dir",
"keyphrases-mcp==0.0.4"
],
"enabled": true
}
}
}{
"mcpServers": {
"keyphrases-mcp": {
"command": "uvx",
"args": [
"keyphrases-mcp-server",
"--allowed-dir",
"keyphrases-mcp==0.0.4"
]
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=keyphrases-mcp&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJrZXlwaHJhc2VzLW1jcC1zZXJ2ZXIiLCItLWFsbG93ZWQtZGlyIiwia2V5cGhyYXNlcy1tY3A9PTAuMC40Il19"
}{
"servers": {
"keyphrases-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"keyphrases-mcp-server",
"--allowed-dir",
"keyphrases-mcp==0.0.4"
]
}
}
}{
"mcpServers": {
"keyphrases-mcp": {
"command": "uvx",
"args": [
"keyphrases-mcp-server",
"--allowed-dir",
"keyphrases-mcp==0.0.4"
]
}
}
}extensions:
"keyphrases-mcp":
enabled: true
name: "keyphrases-mcp"
type: stdio
cmd: "uvx"
args:
- "keyphrases-mcp-server"
- "--allowed-dir"
- "keyphrases-mcp==0.0.4"
timeout: 300
This is a local package: the command runs on your machine.
Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)stability.changes, stability.rug_pulltool list unknowndeps.known_vulns1 advisory to act on (malicious, or rated high or critical with a fix available): GHSA-53q9-r3pm-6pq6 in [email protected] (direct, fixed in 2.6.0); 20 more of lower severity or without a fixdeps.mcp_sdk_versionmcp 2.2.0, no known advisorydeps.resolvable[email protected] resolved: 142 packagesNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo ~liveness-unmeasured -stale-370d
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
[email protected] PyPI141 dependencies, resolved · MCP SDK mcp 2.2.0 · advisories checked 2026-10-19
| advisory | severity | package | fixed in |
|---|---|---|---|
| GHSA-53q9-r3pm-6pq6PyTorch: `torch.load` with `weights_only=True` leads to remote code execution | critical | [email protected]direct | fixed in 2.6.0 |
| GHSA-8mgp-746c-j5xpNLTK: Model-artifact APIs bypass pathsec and touch files outside allowed roots | high | [email protected]indirect | no fix yet |
| GHSA-887c-mr87-cxwpPyTorch Improper Resource Shutdown or Release vulnerability | moderate | [email protected]direct | fixed in 2.8.0 |
| GHSA-vgrw-7cvw-pwgxPyTorch is vulnerable to memory corruption through its unpack_sequence function | moderate | [email protected]direct | fixed in 2.9.1 |
| GHSA-f4hp-rmr7-r7v8PyTorch is Vulnerable to Memory Consumption through pad_packed_sequence Function | moderate | [email protected]direct | no fix yet |
| GHSA-3749-ghw9-m3mgPyTorch susceptible to local Denial of Service | low | [email protected]direct | fixed in 2.7.1-rc1 |
| GHSA-qfhq-4f3w-5fphPyTorch is vulnerable to memory corruption through its torch.lstm_cell function | low | [email protected]direct | fixed in 2.10.0 |
| GHSA-rrmf-rvhw-rf47PyTorch is vulnerable to memory corruption through its torch.jit.script function | low | [email protected]direct | fixed in 2.13.0 |
| GHSA-c678-jfcj-6jmfPyTorch Tuple Handler is Vulnerable to Memory Corruption through Manipulation of None Argument | low | [email protected]direct | no fix yet |
| GHSA-x3gm-94wq-g975PyTorch: Manipulation of the argument scale/zero_point leads to improper initialization via Quantized Sigmoid Module | low | [email protected]direct | no fix yet |
11 more advisories in the dependencies endpoint.
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
keyphrases-mcp | pypi | 0.0.4 | uvx |
No tools observed. Local packages are never executed by the registry.
Schemas: list_tools.
{
"name": "io.github.IvanRublev/keyphrases-mcp",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
"version": "0.0.4",
"packages": [
{
"version": "0.0.4",
"transport": {
"type": "stdio"
},
"identifier": "keyphrases-mcp",
"runtimeHint": "uvx",
"registryType": "pypi",
"runtimeArguments": [
{
"type": "positional",
"value": "keyphrases-mcp-server"
},
{
"name": "--allowed-dir",
"type": "named",
"format": "filepath",
"valueHint": "documents_directory",
"isRequired": true,
"description": "Directory containing documents to process"
}
]
}
],
"repository": {
"url": "https://github.com/IvanRublev/keyphrases-mcp",
"source": "github"
},
"description": "An MCP server to extract keyphrases from a text with the BERT model"
}