Dvalincode MCP server
Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
117 stars56 downloads/wk
Reviews
Write oneNobody has reviewed Dvalincode yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Dvalincode tools (31, 11 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
delete_filewrite actionDelete a file inside the workspace. Used internally by undo for file removal.
dvalin_begin_verificationScan a workspace and persist a compact local verification workflow. Call this only after dvalin_scan reports a finding
dvalin_get_evidenceRender the Markdown audit evidence for a DvalinCode run (defaults to the latest run).
dvalin_get_findingRead one compact finding from a persisted security workflow by fingerprint.
dvalin_get_sessionGet a durable DvalinCode session summary and its latest audit anchor.
dvalin_list_scannersList built-in and optional scanner engines, availability, and reviewable install commands.
dvalin_run_taskwrite actionRun a complete governed coding task inside DvalinCode. Long calls are expected; callers should use a generous timeout.
dvalin_scanScan a workspace for injection, hardcoded secrets, XSS, dynamic code execution, and unsafe shell use.
dvalin_verify_findingsRe-scan a persisted workflow and independently verify that the blocked targets are gone and no new severe findings were introduced.
dvalin_verify_fixRe-derive a Verified Fix Record offline. Recomputes the record hash and re-checks that its verdict follows from its own evidence,
edit_fileReplace exact text in a file. Reports a diff of the change.
git_diffShow the current git diff, optionally scoped to one workspace file. Use before reviewing or summarizing changes.
git_statusShow the current git branch, last 5 commits, and changed files. Use this to understand the git state before making changes.
list_filesList files in the current workspace using a glob pattern.
list_remediation_casesList local remediation cases for the current workspace.
list_skillsList installed DvalinCode skills and the tools they recommend.
memory_deletewrite actionDelete a stale or incorrect local memory entry by id.
memory_importImport memory from Claude Code, Hermes, or a Markdown file/directory into DvalinCode local memory. Use dryRun first to preview candidates.
memory_searchSearch local user/project memory for preferences, project facts, decisions, workflows, and lessons.
memory_updatewrite actionUpdate an existing local memory entry by id. Use to correct stale or imprecise memories.
memory_writewrite actionStore a curated local memory entry. Use for durable preferences, project facts, decisions, workflows, or lessons worth carrying into future sessions.
prepare_remediation_worktreewrite actionCreate an isolated git worktree for a remediation case and update the case status.
project_scriptsList known project scripts and checks from package.json, Makefile, and common Python project files.
read_fileRead a UTF-8 text file from inside the workspace.
read_skillRead an installed DvalinCode skill, including its SKILL.md instructions.
run_checkwrite actionRun a project check such as test, typecheck, build, or lint with structured output. Prefer this over shell for standard validation.
run_security_scanwrite actionRun DvalinCode local security scan on the current workspace and optionally persist findings as remediation cases.
run_security_suitewrite actionRun the Dvalin white-box security suite (built-in rules plus installed Semgrep, Trivy, and OSV-Scanner) and persist remediation cases.
search_textSearch text files in the workspace and return matching lines.
shellwrite actionRun a command in the workspace using the native host shell (cmd.exe on Windows, /bin/sh on Linux and macOS). Git pull/push/fetch/clone and GitHub CLI (gh) operations automatically request outbound network access.
write_filewrite actionWrite content to a file inside the workspace. Reports a diff if the file already exists.
Public scan report
scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it
- Code scan281 source files scanned20/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 2 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- mediumeval / new Function used
exec.evaldist/remediation/localScan.js: … that only documents a risk — `// never eval() user input` — is not * the risk. Only…
Install directly
Runs npx -y dvalincode on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add dvalincode -- npx -y dvalincode
Dvalincode: common questions
- Is Dvalincode MCP server safe?
- Yes, by our scan: it is graded A (85/100). Read the Dvalincode safety report
- How do I install Dvalincode?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Dvalincode need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Dvalincode maintained?
- The last commit was 2 days ago (2026-09-18). The latest release is v0.19.0.
- What can I use instead of Dvalincode?
- Servers from other publishers that do the same job: SkillTotal MCP server, Ausca MCP server and HOL Guard MCP server. Compare all Dvalincode alternatives.
Alternatives to Dvalincode
Same job from other publishers: the closest match first, then the best rated.
- SkillTotalDeterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.not reviewedGrowingB
- AuscaPay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.not reviewedEstablishedB
- HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.not reviewedEstablishedA
- Mushi MushiBug translation for vibe coders: plain-English diagnosis + paste-ready fix in your AI coding agentnot reviewedGrowingA
SomaCheck VibecheckSomaCheck returns proposition-specific Aligned or Unaligned plus model confidence.not reviewedGrowingA