context safety score
A score of 39/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
typosquat
Repository claims to be a Harness CI/CD MCP server using the 'harness-mcp-server' name and registers MCP namespace via HTML comment (<!-- mcp-name: io.github.asklokesh/harness-mcp-server -->), but contains zero implementation code. This is part of a 'LokiMCPUniverse' mass-generated fork pattern that name-squats popular service names in the MCP ecosystem. The repo has 0 stars, 0 forks, no license, and no affiliation with Harness.io. (location: README.md:3)
supply chain
README advertises 'pip install harness-mcp-server' for a package from a repo with no actual Python source code, no setup.py, no pyproject.toml, and no package manifest. This pattern of claiming a PyPI package name for a code-less repo can be used to later publish a malicious package under the squatted name, or to trick users into installing a package that doesn't match this repo's (nonexistent) source. (location: README.md:44)
supply chain
This is a coordinated name-squatting operation. The repo is part of LokiMCPUniverse, an org that mass-generated 23+ brand-name MCP server repos (harness, aws, azure, salesforce, jenkins, gitlab, etc.) within minutes on 2025-06-09 — all containing zero functional code (only a stub __init__.py with a version string). Corresponding PyPI packages were published by user 'slogansand' on 2025-12-30/31. The real Harness company has an official MCP server at harness/mcp-server (created 26 days earlier). The README fraudulently claims 'Comprehensive Harness API coverage', 'Enterprise-ready with rate limiting', and 'Full error handling and retry logic' — none of which exist. The declared entry point (harness_mcp.server:main) references a module that does not exist. The occupied PyPI package name 'harness-mcp-server' could be weaponized at any time with a malicious update. (location: Entire repository and PyPI package 'harness-mcp-server' (owner: slogansand))
typosquat
The server name 'harness-mcp-server' directly impersonates the official Harness CI/CD platform's MCP presence. The real company (harness.io) maintains their official server at github.com/harness/mcp-server. This repo was created 26 days after the official one, by an unaffiliated individual (asklokesh/LokiMCPUniverse) who mass-generated 23 similar repos targeting major brands (AWS, Azure, GCP, Salesforce, ServiceNow, Jenkins, GitLab, Tableau, Power BI, UiPath, etc.). The PyPI package 'harness-mcp-server' blocks the canonical package name for the real Harness organization. (location: Repository name 'harness-mcp-server' and PyPI package 'harness-mcp-server')
curl https://api.brin.sh/mcp/asklokesh%2Fharness-mcp-serverCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
asklokesh/harness-mcp-server currently scores 39/100 with a suspicious verdict and low confidence. The goal is to protect agents from high-risk context before they act on it. Treat this as a decision signal: higher scores suggest lower observed risk, while lower scores mean you should add review or block this mcp server.
Use the score as a policy threshold: 80–100 is safe, 50–79 is caution, 20–49 is suspicious, and 0–19 is dangerous. Teams often auto-allow safe, require human review for caution/suspicious, and block dangerous.
brin evaluates four dimensions: identity (source trust), behavior (runtime patterns), content (malicious instructions), and graph (relationship risk). Analysis runs in tiers: static signals, deterministic pattern checks, then AI semantic analysis when needed.
Identity checks source trust, behavior checks unusual runtime patterns, content checks for malicious instructions, and graph checks risky relationships to other entities. Looking at sub-scores helps you understand why an entity passed or failed.
brin performs risk assessments on external context before it reaches an AI agent. It scores that context for threats like prompt injection, hijacking, credential harvesting, and supply chain attacks, so teams can decide whether to block, review, or proceed safely.
No. A safe verdict means no significant risk signals were detected in this scan. It is not a formal guarantee; assessments are automated and point-in-time, so combine scores with your own controls and periodic re-checks.
Re-check before high-impact actions such as installs, upgrades, connecting MCP servers, executing remote code, or granting secrets. Use the API in CI or runtime gates so decisions are based on the latest scan.
Learn more in threat detection docs, how scoring works, and the API overview.
Assessments are automated and may contain errors. Findings are risk indicators, not confirmed threats. This is a point-in-time assessment; security posture can change.
integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.