How many CVEs have patched _extract_allowed_tools_from_mcp_requests?

1 published CVEs changed _extract_allowed_tools_from_mcp_requests in vllm-project/vllm, in 2 distinct patches totalling 39 changed lines, between 2026 and 2026.

What is the latest CVE that changed _extract_allowed_tools_from_mcp_requests?

CVE-2026-105752 (vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle), published 2026-10-05, changed lines 95 of vllm/entrypoints/openai/responses/serving.py.

How does _extract_allowed_tools_from_mcp_requests compare to the rest of vllm-project/vllm?

vllm-project/vllm has 83 CVEs with a located fix in total; 1 of them changed _extract_allowed_tools_from_mcp_requests.

What do the line numbers refer to?

Line numbers are in the fixed version of the file, as the upstream patch left it. A CVE whose fix was backported to several branches is listed once, with the lines from the upstream commit.

RadicalNotion.AI

Security data

Weaknesses (CWE)The MITRE CWE weakness catalog
Attack Patterns (CAPEC)MITRE CAPEC attack patterns
CNAsNumbering authorities and report cards
VendorsVulnerabilities by vendor
Patched FunctionsWhere CVE fixes land in code

Tools

CVSS CalculatorScore CVSS 4.0, 3.1, 3.0 & 2.0
Badge BuilderEmbeddable SVG badges for READMEs

Resources

LearnSecurity guides
Data SourcesCVE data sources

About Blog Pricing Demo

Home
Patched Functions
Vllm Project
Vllm
_extract_allowed_tools_from_mcp_requests

RadicalNotion.AI

We do not sell or share your personal information.

Security Data

CWE Directory
CAPEC Directory
CNA Directory
CNA Leaderboard
CNA Report Cards
Vendor Directory
Patched Functions
Data Sources

Calculators

CVSS Calculator
CVSS 4.0
CVSS 3.1
CVSS 3.0
CVSS 2.0
Badge Builder

Platform

My Vulnerabilities
Insights
Notifications
Pricing

Learn

Guides
What is a CVE?
What is CVSS?
The CISA KEV catalog
What is EPSS?

Company

About
Blog
Careers
Contact
Demo

Account

Legal

Security
Privacy
Terms

RadicalNotion.AI

Security data

Weaknesses (CWE)The MITRE CWE weakness catalog
Attack Patterns (CAPEC)MITRE CAPEC attack patterns
CNAsNumbering authorities and report cards
VendorsVulnerabilities by vendor
Patched FunctionsWhere CVE fixes land in code

Tools

CVSS CalculatorScore CVSS 4.0, 3.1, 3.0 & 2.0
Badge BuilderEmbeddable SVG badges for READMEs

Resources

LearnSecurity guides
Data SourcesCVE data sources

About Blog Pricing Demo

Home
Patched Functions
Vllm Project
Vllm
_extract_allowed_tools_from_mcp_requests

_extract_allowed_tools_from_mcp_requests in vllm-project/vllm: Patched by 1 CVEs

vllm-project/vllm

Function

_extract_allowed_tools_from_mcp_requests

Name: _extract_allowed_tools_from_mcp_requests in vllm-project/vllm: CVE fixes
Creator: RadicalNotion.AI
License: https://creativecommons.org/licenses/by-nc/4.0/

vllm/entrypoints/openai/responses/serving.py

Last patched October 5, 2026

CVEs

That changed this function

Distinct patches

Backports counted once

Lines changed

Added plus removed

2026

Years

By CVE publication date

Overview

_extract_allowed_tools_from_mcp_requests in vllm-project/vllm was changed by 1 published CVE fixes in 2026, in 2 distinct patches that added or removed 39 lines in total.

vllm-project/vllm has 83 CVEs with a located fix in total, so 1% of them touched this function.

CVEs that patched it

Every published CVE whose fix changed _extract_allowed_tools_from_mcp_requests, newest first, with the lines each fix touched.

vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle
CVE-2026-105752 · line 95 · +0 −39
Low · CVSS 3.1
EPSS 0.2%2026-10-05

Get an alert when the next CVE fix lands in vllm-project/vllm, with the patched functions.

Monitor vllm CVEs

Other functions in these files

Functions in the same file that CVE fixes also changed.

1_create_responsesvllm/entrypoints/openai/responses/serving.py1 CVEs · 2 patches2026
2_generate_with_builtin_toolsvllm/entrypoints/openai/responses/serving.py1 CVEs · 2 patches2026
3_get_harmony_builtin_tool_descriptionsvllm/entrypoints/openai/responses/serving.py1 CVEs · 2 patches2026
4__init__vllm/entrypoints/openai/responses/serving.py1 CVEs · 2 patches2026
5_make_requestvllm/entrypoints/openai/responses/serving.py1 CVEs · 2 patches2026
6_make_request_with_harmonyvllm/entrypoints/openai/responses/serving.py1 CVEs · 2 patches2026
7_render_resolved_response_inputsvllm/entrypoints/openai/responses/serving.py1 CVEs · 2 patches2026

Other hotspots in the repository

Functions in vllm-project/vllm changed by the most CVE fixes.

validate_xgrammar_grammar4 CVEs · vllm/v1/structured_output/backend_xgrammar.py load_bytes3 CVEs · vllm/multimodal/media/audio.py _resolve_rust_frontend_path3 CVEs · vllm/envs.py load_file3 CVEs · vllm/multimodal/media/audio.py __init__3 CVEs · vllm/model_executor/models/kimi_k25.py _try_resolve_transformers3 CVEs · vllm/model_executor/models/registry.py

All patched functions in vllm-project/vllm

Frequently asked questions

Common questions about CVE fixes to _extract_allowed_tools_from_mcp_requests.

How many CVEs have patched _extract_allowed_tools_from_mcp_requests?: 1 published CVEs changed _extract_allowed_tools_from_mcp_requests in vllm-project/vllm, in 2 distinct patches totalling 39 changed lines, between 2026 and 2026.
What is the latest CVE that changed _extract_allowed_tools_from_mcp_requests?: CVE-2026-105752 (vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle), published 2026-10-05, changed lines 95 of vllm/entrypoints/openai/responses/serving.py.
How does _extract_allowed_tools_from_mcp_requests compare to the rest of vllm-project/vllm?: vllm-project/vllm has 83 CVEs with a located fix in total; 1 of them changed _extract_allowed_tools_from_mcp_requests.
What do the line numbers refer to?: Line numbers are in the fixed version of the file, as the upstream patch left it. A CVE whose fix was backported to several branches is listed once, with the lines from the upstream commit.

References

vllm/entrypoints/openai/responses/serving.py on GitHub (opens in a new tab)
All patched functions in vllm-project/vllm
Patched functions directory

Fix locations are computed by RadicalNotion.AI from the upstream patch diff of each CVE. CVE data is sourced from the CVE Program.

Track vllm-project/vllm CVEs

Get an alert when a new CVE lands in this repository, with the patched functions and AI-written remediation guidance.

Create an account See pricing

On this page

Overview
CVEs that patched it
Other functions in these files
Other hotspots in the repository
FAQ
References