Sanitizes and enhances user messages before LLM calls, preventing prompt injection and returning security status for agent protection.
MIT
478,959 tools. Updated 2026-08-26 14:35
"Connecting external data sources for contextual LLM calls" matching MCP tools:
- Creates external data sources for Salesforce Connect, enabling read-write access to external data via OData, SimpleURL, Apex, or other adapters without importing records.MIT
- Create External Objects (__x) linked to External Data Sources to bring external data into Salesforce with lookups, related lists, and reports.MIT
- Fetch external metadata from Wikipedia, TMDB, and TVDB to enrich Plex library items, providing informed discovery and trend analysis beyond native Plex data.MIT
- Get contextual guidance for using BookStack MCP tools, covering topics like authentication, content creation, user management, search, and best practices.MIT
- List attached AI sources and external review targets to manage memory sources in Codex.MIT
Matching MCP Servers
- FlicenseNot gradedqualityCmaintenanceRead-only MCP server exposing homelab data sources (files, mail, calls) to Cloudflare OS, enabling read-only access to documents, emails, and call records.
- FlicenseCqualityDmaintenanceProvides RAG (Retrieval-Augmented Generation) capabilities via Contextual AI, enabling query processing and context-aware responses with citations. Integrates with MCP clients like Cursor IDE and Claude Desktop.1
Matching MCP Connectors
Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.
Find where to buy peptides from vetted, COA-tested vendors and check if a peptide vendor is legit.
- Scan mounted external sources to index their content for retrieval and search.MIT
- Retrieve historical stock price data from local cache. Avoid external API calls by checking what data is available locally for a ticker and date range.MIT
- Run contextualization on private source's pending chunks, re-embed them locally, and mark them enriched. Public sources are already contextual.
- Suggests fixes for code errors by analyzing error messages and contextual data against historical error patterns.MIT
- Identify flaky tests by scanning for timing dependencies, random data, and external HTTP calls, using pytest failure cache for history.MIT
- Check the authentication status of external data sources linked to a knowledge base. Verify connections and identify auth issues quickly.
- Lists the internal functions and methods a file calls, showing its outgoing call edges while omitting external library calls.MIT
- Wire external data sources (weather, sensors, follower counts) to custom numeric parameters of a COMP. Specify channel-to-param mappings with range remapping and optional smoothing for jittery data.MIT
- Validate workflow structure by checking DAG cycles, dependency references, and model ID format without LLM calls to ensure proper configuration before execution.MIT
- Map all agent dependencies—models, connectors, and sub-agents—with call counts and timestamps. Identify which agents rely on a specific LLM before replacing it.MIT
- List all functions called by a given function, categorized as internal, external, or library calls. Identifies low-level calls for tracing dependencies and control flow.AGPL 3.0
- Search all captured LLM calls by prompt, output, agent, or user ID to locate specific calls, errors, or topics. Returns compact summaries with action IDs for deeper analysis.MIT
- Create versioned data assets from S3, GCP, computation results, or combined sources for computational workflows in Code Ocean. Supports internal storage or external references without copying.MIT
- Import content from external sources like Slack, Telegram, or Git with provenance tracking, normalization, and deduplication. Ensures accurate source attribution for every piece of content.MIT