MCP.Market

Veris MCP server

by vighriday·io.github.vighriday/veris·v2.1.8·1 stars
No reviews yet

Behavioral verification intelligence for AI coding agents. 17 MCP tools. Local-first. MIT.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

1 stars108 downloads/wk

Reviews

Write one

Nobody has reviewed Veris yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Veris tools (17, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • allocate_budget

    Given a budget in minutes, greedy-allocates the highest-leverage subset of verification targets. Leverage = (tier × workflow criticality × risk) / estimated cost.

  • analyze_pr_behavior

    Computes real git-worktree diff vs base ref (defaults: origin/main, main, HEAD~1), returns impacted workflows and risk scores. Synthetic 70% slice fallback when no git base available.

  • analyze_repository

    Analyzes the repository AST and returns file/entity counts. First step in the chain.

  • analyze_workflow

    Deep-dive on a single workflow: members, inference signals, top risks, runtime risk hypotheses.

  • confidence_history

    Returns confidence + execution depth trend over the last N runs from local state.

  • cross_repo_snapshot

    Returns the latest confidence + drift snapshot across all repos registered in ~/.veris/registry.json. Useful when a workflow spans services.

  • detect_drift

    Compares current workflow fingerprints against prior runs in state.db. Surfaces silent rewrites (same members, different topology), surface expansion/contraction, and oscillating refactors.

  • export_behavioral_graph

    Returns behavioral graph (nodes + edges, both DependsOn and Invokes). Workflows colored by domain.

  • export_onboardingwrite action

    Writes a workflow-first onboarding map to veris-reports/onboarding/ — one markdown file per workflow, plus an index.

  • generate_adversarial_probes

    Generates concrete Tier 3 adversarial test hypotheses per high-risk node (concurrency, idempotency, retry storms, replay, partial failure, cache stampede, ordering). Each probe has a scenario + expected invariant.

  • generate_verification_plan

    Generates Tier 1/2/3 validation directives keyed to impacted nodes. Tier 3 = adversarial.

  • identify_unverified_behaviors

    Returns confidence score using real execution history (decayed by half-life) + remaining unverified assumptions. Pass executedTargetsCount to override state-derived value.

  • list_workflows

    Auto-clusters the graph into semantic workflow domains (Authentication, Billing, Checkout, Caching, Queue, etc.) and returns per-workflow narrative impact + max/avg risk + runtime risk hypotheses. This is the workflow-first view of the repo.

  • node_history

    Returns execution + risk history for a specific node across all recorded runs.

  • register_repo

    Adds a repo to the user-level cross-repo registry. Subsequent cross_repo_snapshot calls will include it.

  • report_execution

    Closes the feedback loop. External agents (any MCP-compatible coding agent, CI runner) post back verification results — pass/fail/flaky/skipped per nodeId+tier+directive. Confidence math now uses real data instead of a counter.

  • what_if_revert

    Counterfactual: simulates removing the named nodes from the head graph, then recomputes diff + risk vs the actual base. Answers 'what behaviors recover if I revert this?'.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan39 source files scanned25/25
  • –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 20 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Veris compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
17
the typical server has 7
Tools that change things
6%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,688 servers
Downloads a week
108
more than 65% of 12,191 servers with a package

What its tools let an agent do: 13 read · 3 create · 1 change

Install Veris in Claude Code, Cursor or VS Code

Runs npx -y veris-core on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add veris -- npx -y veris-core
Add to Cursor

What the publisher says

From the Veris repository's README, as published. We do not edit it. Read it on GitHub

Veris

veris — Latin, “of truth”

Your agent just changed 40 files.What actually broke, and was any of it checked?

We pointed Veris at Veris — it found 55 defects

Every one is published — what broke, why it mattered, the fix, and the test that proves it: docs/internal/BUGTRACKER.md**

The worst three, in our own tool:

It invented baselines. When git was unavailable, Veris built a "before" state from the first 70% of the current graph and reported the comparison as a real behavioral diff. No flag. No warning. A verification tool was fabricating the thing it verified against.

91% of its call edges were guesses. It matched the trailing name of a call against every declaration sharing that name. console.log() drew an edge to the project's own Logger.log. Measured on a real dependency: 2,804 of 3,077 edges pointed at an ambiguous name.

The graded agent could erase its own failures. Execution results were stored with INSERT OR REPLACE. Post fail, then post pass, and the failure was gone.

We could have fixed these quietly. Publishing them is the point: a tool that tells you what is unverified has no standing to hide its own unverified claims.

This is also the demo. That is the analysis Veris performs, run on itself.

What Veris is

A behavioral diff for AI-written code, speaking the Model Context Protocol so your agent can ask while it is still working — not after you find out in review.

It answers two questions a line diff cannot:

agent-authored PRs at zero coverage of their own changed lines**.

  1. What behavior changed? Not which lines — which behaviors, and what reaches them.
  2. Was any of it actually checked? Published research puts roughly **65% of

Veris never executes anything. No tests, no sandboxes, no runtime. It reads, models, and tells your agent what is at risk and what evidence exists. Running things stays with the tools that are good at running things.

Veris is notBecause A test runnerIt executes nothing. It tells your runner what is worth running. A linter or SAST toolNo rules about style or known-bad patterns. It models behavior change. An "AI guardrail"That means filtering model output. This is about the code the model writes. A coverage toolCoverage says which lines ran. Veris says which behaviors changed and what backs them.

The 30-second version

$ npx veris-core . --base-ref=origin/main

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Veris: common questions

Is Veris MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Veris safety report
How do I install Veris?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Veris need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is Veris maintained?
The last commit was 58 days ago (2026-09-07). The latest release is v2.1.8.
What can I use instead of Veris?
Servers from other publishers that do the same job: Nautilus Compass Memory MCP server.
How does Veris compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 17 (the typical server has 7); tools that change things 6% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Veris

Same job from other publishers: the closest match first, then the best rated.

  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B