ai.contextstudios/mcp

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  pass25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  Scanned 252 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.

• Supply chain

  warn25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  no resolvable repository linked to the package (provenance unverifiable)

• Credential hygiene

  pass15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  pass15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

• Version behavior

  fail10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  vs prior 2.0.0 (minor bump): new tool "ai_project_estimator" appeared; new tool "blog_explorer" appeared; new tool "fetch" touches a sensitive surface (email/exec/net/fs); new tool "get_blog_posts" appeared; new tool "get_company_info" appeared; new tool "get_comparison" appeared; new tool "get_featured_glossary_terms" appeared; new tool "get_glossary_by_tech_stack" appeared; new tool "get_glossary_term" appeared; new tool "get_guide" appeared; new tool "get_location_page" appeared; new tool "get_page" appeared; new tool "get_pricing" appeared; new tool "get_related_glossary_terms" appeared; new tool "get_services" appeared; new tool "list_comparisons" appeared; new tool "list_glossary_categories" appeared; new tool "list_guides" appeared; new tool "list_location_pages" appeared; new tool "request_consultation" touches a sensitive surface (email/exec/net/fs); new tool "search" touches a sensitive surface (email/exec/net/fs); new tool "search_blog_knowledge" touches a sensitive surface (email/exec/net/fs); new tool "search_comparisons" appeared; new tool "search_content" appeared; new tool "search_glossary" appeared; new tool "search_guides" appeared; new tool "search_location_pages" appeared; new tool "search_pages" appeared; new hardcoded outbound host/BCC destination(s): contextstudios-mcp.vercel.app, www.contextstudios.ai.

• Transport config

  pass10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  remote endpoint "https://mcp.contextstudios.ai/api/public/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)