# Cognitive Warfare & PSYOPS MCP (`ryanclinton/cognitive-warfare-psyops-mcp`) Actor Adversarial narrative operation detection and counter-narrative optimization for AI agents via the Model Context Protocol. - **URL**: https://apify.com/ryanclinton/cognitive-warfare-psyops-mcp.md - **Developed by:** [ryan clinton](https://apify.com/ryanclinton) (community) - **Categories:** AI, Developer tools - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing Pay per event + usage This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Cognitive Warfare Psyops MCP Server **Adversarial narrative operation detection and counter-narrative optimization** for AI agents via the Model Context Protocol. This MCP server orchestrates **16 Apify actors** and applies **8 mathematical frameworks** -- SIR-Hawkes epidemiological modeling, DeGroot social learning, Bayesian Stackelberg games, persistent homology, doubly-robust causal inference, Price equation evolutionary dynamics, Morlet wavelet analysis, and q-state Potts statistical physics -- to detect, model, and counter information warfare operations. ### What data can you access? | Data Point | Source | Coverage | |-----------|--------|----------| | Social media posts and engagement | Bluesky Social | Bluesky network | | Community discussions and trends | Hacker News | Tech community | | Encyclopedic context and history | Wikipedia | 6M+ articles | | US federal regulatory activity | Federal Register | All federal actions | | International wanted persons | Interpol Red Notices | Global notices | | Global sanctions and watchlists | OpenSanctions | 100+ programs | | Website content changes | Website Change Monitor | Tracked sites | | Historical content evolution | Wayback Machine | Web Archive | | Country profiles and demographics | REST Countries | All nations | | Global disaster events | GDACS Disaster Alerts | Worldwide | | Congressional legislation | Congress Bills | Current sessions | | Weather events (crisis context) | NOAA Weather | US and global | | Open-source tools and code | GitHub Repo Search | All public repos | | Policy documents (full text) | Website Content to Markdown | Any webpage | | DNS records | DNS Lookup | Any domain | | IP geolocation | IP Geolocation | Global coverage | ### MCP Tools | Tool | Price | Description | |------|-------|-------------| | `detect_narrative_operations` | $0.04 | Detect coordinated narrative operations via coupled SIR-Hawkes epidemiological model. Classifies operation type (amplification/suppression/distortion/fabrication/polarization) with coordination scores. | | `model_belief_dynamics` | $0.04 | Model belief propagation via DeGroot social learning on influence networks. Returns agent belief states, eigenvector centrality, convergence rate (spectral gap), and polarization index. | | `optimize_counter_narrative` | $0.04 | Optimize counter-narrative strategy via Bayesian Stackelberg game with cognitive hierarchy truncation. Returns optimal actions, timing (secretary problem), and Stackelberg payoffs. | | `map_influence_topology` | $0.04 | Map influence network topology via persistent homology (Vietoris-Rips filtration). Returns Betti numbers, persistence diagrams, cluster structure, and Wasserstein distance. | | `attribute_narrative_causation` | $0.04 | Attribute narrative effects to actors via doubly-robust causal inference. Returns causal effects (ATE), propensity scores, Rosenbaum sensitivity, and submodular information gain. | | `simulate_memetic_evolution` | $0.04 | Simulate memetic evolution via Price equation evolutionary dynamics. Returns variant fitness landscape, selection vs transmission bias decomposition, and dominant meme trajectory. | | `detect_cross_scale_coordination` | $0.04 | Detect cross-scale coordinated behavior via Morlet wavelet multi-resolution analysis at individual/group/network/population scales with wavelet power spectra. | | `forecast_polarization_phase_transition` | $0.04 | Forecast polarization phase transitions via q-state Potts model from statistical physics. Returns order parameter, critical temperature, susceptibility, and regime classification. | ### Data Sources - **Bluesky Social** -- Social media posts, engagement metrics, and network connections for narrative propagation analysis - **Hacker News** -- Community discussions and trending topics for narrative velocity measurement - **Wikipedia** -- Encyclopedic context for historical baseline and edit war detection - **Federal Register** -- US regulatory activity for government narrative framing analysis - **Interpol Red Notices** -- International wanted persons for threat actor attribution - **OpenSanctions** -- Global sanctions and PEP data for state actor identification - **Website Change Monitor** -- Content change tracking on media and government websites - **Wayback Machine** -- Historical content for narrative evolution and revision detection - **REST Countries** -- Country profiles for geopolitical context in narrative analysis - **GDACS Disaster Alerts** -- Crisis events that amplify narrative vulnerability - **Congress Bills** -- Legislative activity for political narrative context - **NOAA Weather** -- Weather events creating narrative exploitation windows - **GitHub Repo Search** -- Open-source disinformation detection tools and datasets - **Website Content to Markdown** -- Full-text extraction from policy and media pages - **DNS Lookup** -- Infrastructure attribution for narrative source identification - **IP Geolocation** -- Geographic attribution of digital narrative infrastructure ### How the scoring works Eight mathematical frameworks provide different analytical lenses on information warfare. **SIR-Hawkes Epidemiological Model** couples compartmental epidemic dynamics (Susceptible-Infected-Recovered) with Hawkes self-exciting point process intensity. Infection rate is modulated by narrative intensity, enabling detection of coordinated amplification campaigns. **DeGroot Social Learning** models belief propagation through influence networks. Eigenvector centrality identifies key opinion leaders; spectral gap measures convergence speed; polarization index tracks belief divergence. **Bayesian Stackelberg Game** models counter-narrative as a leader-follower game with cognitive hierarchy truncation. Optimal timing follows the secretary problem framework. Returns Stackelberg payoffs for attacker and defender. **Persistent Homology** via Vietoris-Rips filtration reveals topological features (clusters, loops, voids) in influence networks at multiple scales. Betti numbers quantify structural complexity. **Doubly-Robust Causal Inference** estimates Average Treatment Effect (ATE) of narrative interventions with Rosenbaum sensitivity analysis for hidden confounders. Submodular information gain identifies optimal measurement points. **Price Equation Evolutionary Dynamics** decomposes narrative evolution into selection differential and transmission bias, identifying which narrative variants are winning in the memetic fitness landscape. **Morlet Wavelet Analysis** detects coordination patterns at individual, group, network, and population scales simultaneously. Cross-scale coherence reveals hierarchical coordination structures. **q-State Potts Model** from statistical physics forecasts polarization phase transitions. The order parameter and susceptibility measure how close a population is to a critical transition between consensus and fragmentation. ### How to connect this MCP server #### Claude Desktop ```json { "mcpServers": { "cognitive-warfare-psyops": { "url": "https://cognitive-warfare-psyops-mcp.apify.actor/mcp" } } } ```` #### Programmatic (HTTP) ```bash curl -X POST https://cognitive-warfare-psyops-mcp.apify.actor/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_APIFY_TOKEN" \ -d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"detect_narrative_operations","arguments":{"query":"election interference social media"}},"id":1}' ``` This MCP server also works with **Cursor**, **Windsurf**, **Cline**, and any other MCP-compatible client. ### Use cases for cognitive warfare intelligence #### Government STRATCOM Analysis Detect coordinated narrative operations targeting national narratives with `detect_narrative_operations`. Classify operation type and assess threat level for strategic communications response. #### Counter-Disinformation Strategy Optimize counter-narrative timing and content with `optimize_counter_narrative`. The Bayesian Stackelberg framework identifies optimal response actions against modeled adversary strategies. #### Social Media Platform Integrity Detect cross-scale coordination patterns with `detect_cross_scale_coordination`. Morlet wavelet analysis reveals bot networks and coordinated inauthentic behavior at multiple organizational levels. #### Academic Information Warfare Research Model belief dynamics with `model_belief_dynamics` and simulate memetic evolution with `simulate_memetic_evolution` for academic research on information ecosystems and narrative competition. #### Crisis Communication Vulnerability Assessment Forecast polarization phase transitions with `forecast_polarization_phase_transition` to identify when populations are near critical points where information interventions have outsized impact. #### Attribution and Causal Analysis Attribute narrative effects to specific actors with `attribute_narrative_causation`. Doubly-robust estimation with Rosenbaum sensitivity analysis provides defensible causal claims. ### How much does it cost? All tools cost **$0.04** per call. The **Apify Free plan** includes $5 of monthly credits -- enough for **125 tool calls**. Each call queries up to 16 actors in parallel. ### FAQ **Q: Is this for offensive or defensive use?** A: This is designed for defensive narrative intelligence -- detecting adversarial operations, modeling threats, and optimizing counter-narratives. Responsible use is essential. **Q: How accurate are the mathematical models?** A: The models provide quantitative frameworks for analysis. Results should be interpreted by domain experts. Model accuracy depends on data availability and quality. **Q: Is it legal to use this?** A: All data sources are publicly available. See [Apify's guide on web scraping legality](https://blog.apify.com/is-web-scraping-legal/). **Q: What social platforms are covered?** A: Currently Bluesky for social data, Hacker News for community discussions, and Website Change Monitor for media/government content changes. **Q: Can this detect deepfakes?** A: No. This analyzes narrative patterns and coordination structures, not media content. Deepfake detection requires specialized visual analysis tools. ### Related MCP servers | MCP Server | Focus | |-----------|-------| | [brand-narrative-intelligence-mcp](https://apify.com/ryanclinton/brand-narrative-intelligence-mcp) | Brand-level narrative and reputation monitoring | | [corporate-political-exposure-mcp](https://apify.com/ryanclinton/corporate-political-exposure-mcp) | Political influence and lobbying analysis | | [ai-model-governance-mcp](https://apify.com/ryanclinton/ai-model-governance-mcp) | AI governance and bias research monitoring | ### Integrations This MCP server runs on the **Apify platform** and supports scheduling, webhooks, API access, and dataset export for STRATCOM and OSINT platform integration. # Actor input Schema ## Actor input object example ```json {} ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("ryanclinton/cognitive-warfare-psyops-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = {} # Run the Actor and wait for it to finish run = client.actor("ryanclinton/cognitive-warfare-psyops-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call ryanclinton/cognitive-warfare-psyops-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=ryanclinton/cognitive-warfare-psyops-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Cognitive Warfare & PSYOPS MCP", "description": "Adversarial narrative operation detection and counter-narrative optimization for AI agents via the Model Context Protocol.", "version": "1.0", "x-build-id": "Ecre1mPNIZGyTKnyc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ryanclinton~cognitive-warfare-psyops-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ryanclinton-cognitive-warfare-psyops-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ryanclinton~cognitive-warfare-psyops-mcp/runs": { "post": { "operationId": "runs-sync-ryanclinton-cognitive-warfare-psyops-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ryanclinton~cognitive-warfare-psyops-mcp/run-sync": { "post": { "operationId": "run-sync-ryanclinton-cognitive-warfare-psyops-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": {} }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```