io.github.Omnidim/omnidim-mcp-server

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 205 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

  pass25% of grade

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

  repository linkage verified

• 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.

  Network egress present (package.json depends on HTTP client "axios") — expected for most servers and not a finding on its own. 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

  warn10% of grade

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

  vs prior 0.7.0 (minor bump): new tool "listAgents" appeared; new tool "createAgent" touches a sensitive surface (email/exec/net/fs); new tool "getAgent" appeared; new tool "updateAgent" touches a sensitive surface (email/exec/net/fs); new tool "deleteAgent" touches a sensitive surface (email/exec/net/fs); new tool "dispatchCall" appeared; new tool "listCallLogs" appeared; new tool "getCallLog" appeared; new tool "fetchBulkCalls" appeared; new tool "createBulkCall" appeared; new tool "addBulkCallContact" appeared; new tool "getBulkCall" appeared; new tool "bulkCallActions" appeared; new tool "cancelBulkCall" appeared; new tool "getBulkCallLiveStatus" appeared; new tool "listKnowledgeBaseFiles" appeared; new tool "canUploadFile" touches a sensitive surface (email/exec/net/fs); new tool "uploadKnowledgeBaseFile" touches a sensitive surface (email/exec/net/fs); new tool "attachKnowledgeBaseFiles" appeared; new tool "detachKnowledgeBaseFiles" appeared; new tool "deleteKnowledgeBaseFile" touches a sensitive surface (email/exec/net/fs); new tool "listPhoneNumbers" appeared; new tool "attachPhoneNumber" appeared; new tool "detachPhoneNumber" appeared; new tool "importTwilioNumber" appeared; new tool "importExotelNumber" appeared; new tool "importSipTrunk" appeared; new tool "listLLMProviders" appeared; new tool "listVoices" appeared; new tool "listSTTProviders" appeared; new tool "listTTSProviders" appeared; new tool "listAllProviders" appeared; new tool "getVoice" appeared; new tool "listChildOrganizations" appeared; new tool "addUser" appeared; new tool "setUserAccessControl" appeared; new tool "setUserExpiry" appeared; new tool "setChildConcurrency" touches a sensitive surface (email/exec/net/fs); new tool "calculateCreditOperation" appeared; new tool "transferCreditsToChild" appeared; new tool "revertCreditsFromChild" appeared; new tool "getResellerCreditLogs" appeared.

• 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.omnidim.io/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)