How should authentic-mcp-server be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this mcp.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

authentic-mcp-server answer-first brief

OpenClaw agent: authentic-mcp-server Authentic Verification Layer (MCP Server) **A Local-First Forensic Sidecar for AI Agents** --- The "Why" The Authentic Verification Layer is a Model Context Protocol (MCP) server designed for **local** AI agents (Jan Desktop, Claude Desktop, and other MCP-compatible clients). It acts as a "Forensic Sidecar," providing advanced text analysis capabilities while maintaining complete privacy and offline operation. **Eco- Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Freshness

Last checked 2/22/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

authentic-mcp-server is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 98/100

authentic-mcp-server

MCPverified

Public facts

Change events

Artifacts

Freshness

Feb 22, 2026

Verifiededitorial-content1 verified compatibility signal

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

Schema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

MCP

Freshness

Feb 22, 2026

Vendor

Robotwist

Artifacts

Benchmarks

Last release

1.0.0

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Published capability contract available. No trust telemetry is available yet. Last updated 2/24/2026.

View Source

Setup snapshot

git clone https://github.com/robotwist/authentic-mcp-server.git

1
Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Robotwist

profilemedium

Observed Feb 24, 2026Source link Provenance

Compatibility (2)

Protocol compatibility

MCP

contracthigh

Observed Feb 24, 2026Source link Provenance

Auth modes

mcp, api_key

contracthigh

Observed Feb 24, 2026Source link Provenance

Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh

Observed Feb 24, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB MCP

Extracted files

Examples

Snippets

Languages

typescript

Executable Examples

mermaid

flowchart TD
    A[User Query] --> B{Power Gate}
    B -->|Block| E[Return Error]
    B -->|Pass| C{Truth Gate}
    C -->|Block| E
    C -->|Pass| D[MCP Tool Handler]
    D --> F[Ollama API<br/>localhost:11434]
    F --> G[llama3:latest]
    G --> H[JSON Result]
    H --> I[Return to Client]
    
    style B fill:#ffd93d
    style C fill:#ff6b6b
    style F fill:#6bcf7f
    style G fill:#6bcf7f

bash

ollama pull llama3:latest

bash

git clone <repository-url>
   cd authentic-mcp-server

bash

npm install

bash

npx tsc

bash

curl http://localhost:11434/api/tags

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB MCP

Docs source

GITHUB MCP

Editorial quality

ready

Full README

Authentic Verification Layer (MCP Server)

A Local-First Forensic Sidecar for AI Agents

The "Why"

The Authentic Verification Layer is a Model Context Protocol (MCP) server designed for local AI agents (Jan Desktop, Claude Desktop, and other MCP-compatible clients). It acts as a "Forensic Sidecar," providing advanced text analysis capabilities while maintaining complete privacy and offline operation.

Eco-Epistemic Architecture: This server solves two critical problems facing local AI deployments:

Battery Drain: Heavy GPU workloads can quickly deplete device batteries. Our "Power Gate" circuit breaker blocks oversized inputs before they reach the GPU.
Hallucination: Unverified or unverifiable content leads to unreliable analysis. Our "Truth Gate" boolean filter blocks subjective content, gibberish, and dangerous patterns before AI processing.

All analysis runs through Boolean Gates (Truth Gate, Power Gate) that execute before waking up the GPU, ensuring zero wasted compute on blocked content.

Features (The Tools)

The server exposes three forensic analysis tools powered by Llama-3 via Ollama:

1. `scan_for_fallacies`

Analyzes text for logical fallacies and cognitive distortions. Returns a list of detected flaws with confidence ratings.

Inputs:

text (string): The raw text to analyze
power_mode ("eco" | "performance"): Power mode - 'eco' limits input to 2000 chars, 'performance' allows up to 10000 chars

2. `compare_sources`

Performs a semantic "Word Diff" between two texts on the same topic. Highlights how language differs (e.g., 'Riot' vs 'Protest').

Inputs:

source_a (string): Text from the first source
source_b (string): Text from the second source
power_mode ("eco" | "performance"): Power mode - 'eco' limits input to 2000 chars per source, 'performance' allows up to 10000 chars

3. `distill_kernel`

Strips all adjectives, adverbs, and emotional loading from text, leaving only the verifiable subject-verb-object facts.

Inputs:

text (string): The text to distill
power_mode ("eco" | "performance"): Power mode - 'eco' limits input to 2000 chars, 'performance' allows up to 10000 chars

Architecture

flowchart TD
    A[User Query] --> B{Power Gate}
    B -->|Block| E[Return Error]
    B -->|Pass| C{Truth Gate}
    C -->|Block| E
    C -->|Pass| D[MCP Tool Handler]
    D --> F[Ollama API<br/>localhost:11434]
    F --> G[llama3:latest]
    G --> H[JSON Result]
    H --> I[Return to Client]
    
    style B fill:#ffd93d
    style C fill:#ff6b6b
    style F fill:#6bcf7f
    style G fill:#6bcf7f

Flow:

User Query → Tool request with input text
Power Gate → Circuit breaker (blocks oversized inputs in "eco" mode - fastest check)
Truth Gate → Heuristic filter (blocks gibberish, spam, dangerous patterns, pure opinion)
MCP Tool → Routes to appropriate handler (scan_for_fallacies, compare_sources, or distill_kernel)
Ollama → Local LLM API call to http://localhost:11434/api/generate
JSON Result → Parsed response returned to client

Installation & Setup

Prerequisites

Node.js (v18 or higher)
Ollama installed and running locally
- Download: https://ollama.ai
- Verify installation: ollama --version
Llama-3 model pulled in Ollama:
```
ollama pull llama3:latest
```

Installation Steps

Clone the repository:

git clone <repository-url>
cd authentic-mcp-server

Install dependencies:
```
npm install
```
Build the TypeScript code:
```
npx tsc
```
This compiles the source files in src/ to JavaScript (same directory).
Verify Ollama is running:
```
curl http://localhost:11434/api/tags
```

Configuration for Jan Desktop

To use this server with Jan Desktop:

Open Jan Desktop Settings
Navigate to MCP Servers
Click Add Server or Edit an existing entry
Configure as follows:

Command: node

Args: /absolute/path/to/authentic-mcp-server/src/index.js

Example:
```
/home/robwistrand/authentic-mcp-server/src/index.js
```
Note: Use the absolute path to the compiled index.js file (not index.ts).
Restart Jan Desktop to load the server

The server uses stdio transport (standard input/output), so no port configuration is needed.

Troubleshooting

"No Console Log" Rule

Important: This server uses stdio transport for MCP communication. stdout is reserved exclusively for JSON-RPC messages. All logging, debugging, and status messages use console.error() (which writes to stderr).

If you see console.log() in the code, it will break the MCP protocol. Use console.error() instead.

Jan GPU Crash Fix

If Jan Desktop crashes with GPU-related errors (e.g., libcudart.so not found):

Switch to CPU mode in Jan Desktop settings
Or configure Ollama to use CPU/Vulkan:
```
export OLLAMA_NUM_GPU=0
ollama serve
```

This forces Ollama to run on CPU instead of GPU, avoiding CUDA dependency issues.

Ollama Connection Issues

Connection refused: Ensure Ollama is running (ollama serve)
Model not found: Pull the model (ollama pull llama3:latest)
Timeout errors: Check system resources (CPU/RAM) - Llama-3 requires significant resources

Gate Blocking Issues

Power Gate: Input exceeds character limit for selected power_mode
- Solution: Use power_mode: "performance" or reduce input length
Truth Gate: Content appears to be gibberish, spam, or pure opinion
- Solution: Provide substantive, verifiable content

License

MIT

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

Verifiedcapability-contract

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

ready

Auth

mcp, api_key

Streaming

Data region

global

Protocol support

MCP: verified

Requires: mcp, lang:typescript

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.

Trust confidence is not low and verification freshness is acceptable.

Protocol support is explicitly confirmed in contract metadata.

Invocation examples

curl -s "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/snapshot"

curl -s "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract"

curl -s "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

Ard RegistryUpdated 6h agoRank 94

ShortlistLens

Structured website and review evidence for AI-assisted local-business shortlisting.

MCPmcpmcp-registry

Ard RegistryUpdated 6h agoRank 94

Inferventis MCP Server

Loan & mortgage calculator, compound interest, ROI, crypto prices, FX conversion for AI agents.

MCPmcpmcp-registry

Ard RegistryUpdated 6h agoRank 94

io.github.cyanheads/reliefweb-mcp-server

Search ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP.

MCPmcpmcp-registry

Ard RegistryUpdated 6h agoRank 94

io.github.Deesmo/arch-tools-mcp

63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.

MCPmcpmcp-registry

Machine Appendix

Contract JSON

{
  "contractStatus": "ready",
  "authModes": [
    "mcp",
    "api_key"
  ],
  "requires": [
    "mcp",
    "lang:typescript"
  ],
  "forbidden": [],
  "supportsMcp": true,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": "https://github.com/robotwist/authentic-mcp-server#input",
  "outputSchemaRef": "https://github.com/robotwist/authentic-mcp-server#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:46:38.738Z",
  "sourceUpdatedAt": "2026-02-24T19:46:38.738Z",
  "freshnessSeconds": 19574594
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "MCP"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_MCP",
      "generatedAt": "2026-10-09T09:09:53.235Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "MCP",
      "type": "protocol",
      "support": "supported",
      "confidenceSource": "contract",
      "notes": "Confirmed by capability contract"
    }
  ],
  "flattenedTokens": "protocol:MCP|supported|contract"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "MCP",
    "href": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:38.738Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "mcp, api_key",
    "href": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:38.738Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/robotwist/authentic-mcp-server#input",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:46:38.738Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Robotwist",
    "href": "https://github.com/robotwist/authentic-mcp-server",
    "sourceUrl": "https://github.com/robotwist/authentic-mcp-server",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/mcp-robotwist-authentic-mcp-server/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

authentic-mcp-server answer-first brief

Executive Summary

Evidence Ledger

Release & Crawl Timeline

Artifacts Archive

Docs & README

Authentic Verification Layer (MCP Server)

The "Why"

Features (The Tools)

1. scan_for_fallacies

2. compare_sources

3. distill_kernel

Architecture

Installation & Setup

Prerequisites

Installation Steps

Configuration for Jan Desktop

Troubleshooting

"No Console Log" Rule

Jan GPU Crash Fix

Ollama Connection Issues

Gate Blocking Issues

License

Contract & API

Reliability & Benchmarks

Media & Demo

Related Agents

ShortlistLens

Inferventis MCP Server

io.github.cyanheads/reliefweb-mcp-server

io.github.Deesmo/arch-tools-mcp

1. `scan_for_fallacies`

2. `compare_sources`

3. `distill_kernel`