Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Okareo
MCP serversSimulation, evaluation and monitoring for voice agents.
-
calcport
MCP serversSafe arithmetic: evaluate expressions and add, subtract, multiply, divide.
@reneturcios/calcport@0.1.0 -
web-eval-agent
MCP serversAn MCP server that autonomously evaluates web applications.
git clone https://github.com/refreshdotdev/web-eval-agent.git -
mcp
MCP serversMCP server providing OpenFeature SDK installation guides and OFREP flag evaluation
@openfeature/mcp@0.0.22 -
Data Observability
MCP serversSQL data health analyzer and pipeline observability evaluator.
-
calculator-mcp-server
MCP serversEvaluate, simplify, and differentiate mathematical expressions.
@cyanheads/calculator-mcp-server@0.6.0 -
Uncertainty Calculator
MCP serversEvaluate mathematical expressions and propagate measurement uncertainty.
-
RecourseOS
MCP serversConsequence evaluation for AI agents. Check recoverability before destructive actions.
recourse-cli@0.1.12 -
ADHDEvaluations
MCP servers9,846 ADHD evaluation providers from the CMS NPI Registry.
-
RAGScore
MCP serversGenerate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
ragscore@0.8.6 -
Bulwark
MCP serversAI agent governance: content scanning, audit logs, policy evaluation, session management.
ghcr.io/bpolania/bulwark:v0.2.0 -
Calc Eval
MCP serversEvaluate a+b style arithmetic. Expression discarded.
-
surfbird-mcp
MCP serversSelf-hosted Kitesurf headless browser: markdown, screenshots, PDF, evaluate, batch.
surfbird-mcp@0.1.2 -
samyama-graph
MCP serversRust graph-vector database: OpenCypher (99.9% of evaluated TCK scenarios pass), vector search, graph algorithms, RESP + HTTP. LDBC SNB Interactive and BI complete; 1B edges on one machine.
git clone https://github.com/samyama-ai/samyama-graph.git -
PromptOT
MCP serversManage, version, and publish LLM prompts with blocks, variables, and evaluations.
@prompt-ot/mcp@0.1.2 -
RUNaDIVA
MCP serversAutonomous Decision Intelligence for evaluating economic decisions before value is committed.
-
AgentPing
MCP serversProduction observability for AI agents: search runs, read evaluations, acknowledge incidents.
-
BIGHUB
MCP serversDecision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.
@bighub/bighub-mcp@0.2.1 -
CreditRisk Oracle
MCP serversB2B credit risk evaluator and supply chain health scoring oracle.
-
PromptBranch
MCP serversLocal-first MCP server for versioning, searching, evaluating, and improving AI prompts.
@promptbranch/mcp@0.2.6 -
PolyAccounts accounting
MCP serversCompany-scoped accounting reads, writes and workflows. Supervised synthetic evaluation only.
https://github.com/andrewblount/polyaccounts-agent-kit/releases/download/v1.0.2/polyaccounts-hosted.mcpb@1.0.2 -
mcp-prowl
MCP serversDiscover, evaluate, and compare SaaS APIs. Agent-verified scores and metrics.
mcp-prowl@0.1.1 -
Ask Jev
MCP serversEvaluate state with typed choice, score, and probability questions.
-
Apricot
MCP serversManage SysML2 projects; check, evaluate, verify, query, document and diagram models.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.