Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Persuasion Detector Analyze this news article for Cialdini's six persuasion principles"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP-based agent that analyzes text (news articles, ads, political messaging, chatbot output) for the presence of Cialdini's six principles of persuasion (Reciprocity, Commitment/Consistency, Social Proof, Authority, Liking, Scarcity). Built for journalists and media researchers who want a structured, evidence-backed read on how a piece of text is trying to persuade its reader, not just whether it is.
This project grew out of my background in social psychology (personality and social psychology were my strongest areas) combined with prior work on news trust and content provenance at SFI MediaFutures. It's deliberately built as a production-oriented tool, not a notebook demo. The file structure below mirrors the components you'd expect in a real internal AI platform (access control, guardrails, observability, retrieval), rather than an idealized, all-in-one script.
Most "persuasion detection" demos either hardcode a handful of keyword rules, or throw raw text at an LLM with no grounding and no guardrails. This project tries to do better on both fronts:
Grounded, not just prompted. Scoring is backed by a small retrieval-augmented (RAG) pipeline: labeled reference examples are embedded via Voyage AI and stored in a local vector database (Chroma), so the model has concrete precedent to reason from, not just a bare list of principle names.
Guarded, not just trusted. Input is validated for length and checked (via regex pattern-matching) for common prompt-injection attempts before it ever reaches the model. The model's own output is constrained with a Pydantic schema: Claude cannot return a persuasion score outside 0 to 1, or a principle name outside the real six.
Observable, not a black box. Every request is logged, with deliberate care not to log raw user text, for GDPR reasons, so the system's behavior over time (rejection rates, failure rates) is actually inspectable.
Related MCP server: Cold Email & Outreach MCP Server
``` Text input │ ▼ Guardrails (length + injection checks) │ ▼ Retrieval (Voyage embeddings + Chroma vector search) │ ▼ Prompt construction (delimited user text + principle definitions + examples) │ ▼ Claude (structured output via Pydantic schema) │ ▼ Formatted persuasion report ```
The structure deliberately separates concerns the way a production AI platform typically would: access/model configuration, guardrails and policy, observability, and retrieval, rather than one monolithic script:
File | Platform concern | What it does |
| Access / model configuration | Centralizes API keys, model selection, and tuning parameters; fails fast if required secrets are missing |
| Guardrails, policy, compliance | Input length validation, regex-based prompt-injection detection, Pydantic-enforced output schema |
| Logging and security monitoring | Structured logging to console and file; deliberately excludes raw user text from logs |
| Domain knowledge | Definitions of Cialdini's six principles, used both for scoring guidance and as the schema's source of truth |
| AI-recognition/RAG | Labeled example set, embedded via Voyage AI and retrieved via Chroma vector search to ground each analysis |
| MCP integration | The MCP tool itself, orchestrating the full pipeline end to end |
| Quality assurance | pytest coverage of the guardrail functions, including a regression test for a prompt-injection variant the original substring-matching approach missed |
Language model: Claude (Anthropic API), structured output via
client.messages.parse() and a Pydantic schema
Embeddings / retrieval: Voyage AI + ChromaDB (local, persistent vector store)
Protocol: Model Context Protocol (MCP), via the official mcp
Python SDK
Validation: Pydantic v2
Testing: pytest
The six persuasion principles are defined in two places: as a Literal
type constraint in guardrails.py, and as full definitions in
principles.py. This is intentional, not an oversight. The Literal
constraint is a strict, independent safety gate on the model's output,
kept hardcoded so that a change to the content source
(principles.py) can never silently loosen what's accepted as valid.
No content moderation or topic filtering. Journalists legitimately need to write about difficult subjects. The tool's job is to identify persuasive technique, not to police topic, and conflating the two would undermine its actual purpose.
Informed by patterns from NVIDIA's NeMo Guardrails framework, though not taken as a dependency. This project's guardrail surface is narrow enough that a full general-purpose framework would have added complexity without a matching benefit.
This server cannot be deployed
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Hallucination & safety checks for LLM/Agent outputs: claim-level fact-check with citations.
Help your AI improve landing pages, grounded in 3,500+ scored sections and 500 real pages.
Experimental GDPR grounding: rules, preconditions, exceptions, exact quotes, and citation checks.
