- Conduid
- Marketplace
- #evidence
MCP servers tagged evidence
24 live MCP servers tagged "evidence", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with evidence.
Agent Inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.
Omk
Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents. Routes tasks into scoped DAG lanes with replayable artifacts.
Xenon
🚀 Xenon — Agent Harness for AI coding agents. 证据导向架构 + 7种推理范式 + 执行隔离边界 + SWE-bench 40% 通过率（+6.7pp）。可信、可验证、可评测的 AI Agent 运行时。
AegisFlow
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
Knows MCP Server
A Model Context Protocol (MCP) server that integrates with the KnowS evidence & question-answering API.
Research Os
Local-first research control plane for gated source packs, claim truth, contradiction handling, and long-running AI synthesis
Across Orchestrator
Durable execution, quality gates, and evidence for supervised agent workflows.
Cockroach Crawler
Give AI agents bounded eyes on the public web: crawl, search, and normalize evidence without an unrestricted browser.
Codex Native Long Video Memory
Local-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.
Claims Ledger
Source-anchored claims ledgers for codebases and AI agents — CI-gated evidence verification. No anchor, no claim.
Dsh Config Origin Proof
Content-addressed DSH configuration origin and shadowing evidence
Readproof
Readproof — the lockfile and replay primitive for what AI agents read: stable identity, freshness policy, content-addressed snapshots, per-run manifests, diff, byte-exact replay,…
Research Connector Hub
Local-first research evidence and structured brief MVP with CLI and a bounded MCP adapter.
Vzt Browser
Aside-class browser agent — MCP · CLI · REPL. A real logged-in browser for AI agents: Keychain credential vault (secrets never in model context), enforced approval + read-only evi…
Novoriq Chargeback Operations
AI-native chargeback operations MCP for dispute monitoring, evidence workflows, and revenue recovery infrastructure.
Norms MCP Engine
Fail-closed evidentiary eligibility engine for AI-agent norms, with a self-linting claim map.
Proofspec
Claims are cheap. Proofspec makes them executable — evidence contracts, claim graphs, hash-chained receipts, CI gates, reports, and MCP for public software claims.
Evidence Normalizer
men (MCP Evidence Normalizer) — deterministic normalization of MCP tool results into clean, bounded evidence.
Miseledger
Your agent history is scattered. MiseLedger makes it searchable evidence. Local SQLite FTS ledger for AI work history; Brigade-ready evidence bundles. No network.
Forsety
Evidence layer for licensed AI data access — Built on Shelby Protocol
Productarena
The open evidence layer for the agent economy — arenas, processes, proofs, and simulations measuring how ready software is for AI agents. Every verdict cited, probed, and contesta…
Dsh Surface Contract Proof
Content-addressed conformance proof across recorded DSH ToolRuntime, MCP JSON-RPC and CLI JSON surfaces
Roshambo Starmap
Evidence artefact of the Roshambo field run: 27 agents from five vendors on two machines built an invented star chart under lease discipline - 1,226 collisions, never two winners.…
Gaps Qa
Evidence-first browser QA and MCP auditing system with Playwright/CDP and Markdown, JSON, and DOCX report bundles.