trybEvidence-first beta
MCP Security Observatory
The complete latest official Registry sweep, separated from static and execution scan coverage. Absence of findings is never presented as a safety claim.
Security Index
Pending
0 comparable scans
Monitored
0
Public server identities
High risk
0
Latest completed scan
Open findings
0
Public, non-embargoed
Disclosures
0
Responsible disclosure records
30229 canonical servers
Page 177 of 1512
anonym-community-mcp
Read-only MCP server that exposes the anonym.community privacy research corpus via typed tools, letting agents search 1,478 PII pain points, jurisdiction laws, FAQ entries, and 1,600+ papers with citations. Enables precise, citable answers about privacy law and data-protection issues directly from MCP clients.
vunversioned · static queued · execution queued
ariba-mcp
A metadata-driven MCP server that exposes selected SAP Ariba OpenAPI operations as configurable tools, enabling secure interaction with Ariba APIs through natural language.
vunversioned · static queued · execution queued
asana-mcp
An MCP server for Asana that accesses every workspace using a personal access token, enabling task and project management through integrated tools like list, create, and complete tasks.
vunversioned · static queued · execution queued
@batontasks/mcp
MCP server for the Baton task tracker, enabling AI agents to manage tasks, process inbox events, and collaborate with humans via natural language. Wraps the Baton REST API with 12 tools over stdio.
vunversioned · static queued · execution queued
bitrix24-mcp-server
A secure, self-hosted MCP server for Bitrix24 CRM that enables reading CRM data and performing confirmation-gated writes through schema discovery and OAuth integration.
vunversioned · static queued · execution queued
caniemail
MCP server providing email client compatibility data from caniemail.com, enabling agents to lint HTML/CSS for email client support, check feature support across clients, and search for features by keyword, with verdicts including supported, unsupported, mitigated, and untested.
vunversioned · static queued · execution queued
cart-mcp
Computes soil resource concern ratings for an area of interest using USDA Soil Data Access and exposes them as MCP tools, resources, and prompts for AI-assisted conservation planning.
vunversioned · static queued · execution queued
Catalyst Edge MCP
Provides read-only tools to retrieve source-linked catalyst evidence dossiers for public-company tickers, including deterministic catalyst scores and paged source records.
vunversioned · static queued · execution queued
CatHub Nyaanes
Enables orchestrating multiple AI CLI agents (Codex, Grok, Claude, etc.) via Claude Code, providing tools for dispatching tasks, broadcasting, debating, and managing jobs through a local MCP server.
vunversioned · static queued · execution queued
Causal Inference MCP Server
An MCP server that exposes causal inference methods (difference-in-differences, synthetic control, propensity matching, and assumption checks) as callable tools, enabling AI agents to run deterministic statistical analyses instead of computing them inline.
vunversioned · static queued · execution queued
@clikta/mcp-server
Enables Claude to drive a real browser and automatically turn interactions into Clikta interactive demos, step-by-step guides, and narrated videos.
vunversioned · static queued · execution queued
Daleel
Screens US-listed stocks and ETFs for Sharia compliance, providing auditable verdicts with SEC filing citations and multiple screening methodologies.
vunversioned · static queued · execution queued
databricks_ops_mcp
A governed MCP server exposing Databricks operations as tools for jobs orchestration, SQL execution, notebook creation, Unity Catalog governance, lineage, clusters, and DLT pipelines, with safety features like dry-run and audit logging.
vunversioned · static queued · execution queued
docmancer
Local-first memory for coding agents. Discovers the memory, instructions, and rules Claude Code, Codex, and Cursor already wrote on your machine, combines them into one canonical Markdown tree, and serves grounded, cited recall through tools like ask_memory and canonical_memory.
vunversioned · static queued · execution queued
ds-canon
Read-only MCP server that exposes a design system's tokens, components, conventions, and deprecations as queryable tools, enabling agents to look up canonical values, assess change impact, and detect hardcoded value drift.
vunversioned · static queued · execution queued
ephemeral-reasoning-mcp
Provides an MCP server that decomposes complex problems into ordered, isolated reasoning contexts, yielding compressed summaries before discarding intermediate steps. Enables sequential or parallel step execution with optional verification for more reliable LLM reasoning.
vunversioned · static queued · execution queued
extended-rlm
A self-learning knowledge layer for local LLM chat that answers questions from Markdown files, writes new knowledge back every turn, and provides grounding verdicts.
vunversioned · static queued · execution queued
Foundation MCP
Atom-first long-term memory server for MCP clients with durable knowledge storage, hybrid search, typed relations, and context packing for AI prompts.
vunversioned · static queued · execution queued
foundry-copilot-mcp
Bridges Microsoft Foundry agents and Power BI semantic models into GitHub Copilot Chat, enabling users to query and modify measures as the signed-in user via MCP.
vunversioned · static queued · execution queued
FV Backlog MCP Server
An MCP server for interacting with the Backlog API, enabling AI agents to manage projects, issues, wikis, and more, with support for restricting access to a subset of Backlog projects.
vunversioned · static queued · execution queued
Catalog coverage
Every version record returned by the last completed official Registry cursor sweep.
Static coverage
Metadata and artifact checks completed for the current content-bound revision.
Execution coverage
Sandbox behavior checks; unavailable until a conforming external worker completes them.