Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
mcp
MCP serversProvides UX capabilities to enhance the design output and understanding of AI systems.
-
Goodeye
MCP serversDesign, save, and run outcome-aligned AI workflows and verifiers, with reliable image output.
-
blinkpdf
MCP serversRender Markdown and LLM output into accessible PDF/UA-1 PDFs. No headless Chromium.
-
air
MCP serversAI-optimized tool output compression for read, grep, diff, bash, test, web, search, and more
@10iii/air-mcp-server@0.2.8 -
ai-code-scanner
MCP serversScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
@guardbee/mcp-ai-code-scanner@0.3.2 -
PurRAssist
MCP serversRecovers intent from imperfect AI output: JSON, tool calls, names, paths and Markdown edits.
purrassist-cli@0.1.0 -
Taxonomie Produit
MCP serversClassifies product listings into the official Google Shopping taxonomy (5595 categories). Output ...
-
ai-code-scanner
MCP serversScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
@guardbee/mcp-ai-code-scanner@0.5.1 -
lethe
MCP serversContext GC for LLM agents: offload large tool outputs and recall them to save tokens.
lethe-llm-context@0.6.2 -
guardian-mcp
MCP serversRuntime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid).
ethicore-guardian-mcp@0.1.2 -
Ouroboros
MCP serversPins an acceptance spec; the verify command and expected output never enter the success contract.
ouroboros-ai@0.51.5 -
neuronscope
MCP serversTraces which neurons and attention heads drive a language model's output via MCP tools.
neuronscope-cli@0.1.5 -
A2A Artifact Handoff
MCP serversCompiles source-agent outputs into validated, receiver-ready handoff packages.
-
Iris
MCP serversStop shipping agents on vibes. Score every agent output for quality, safety, and cost.
@iris-eval/mcp-server@0.21.0 -
Scout
MCP serversGo browser automation MCP server with verified actions, durable task recovery, and bounded outputs.
ghcr.io/klarlabs-studio/scout:1.16.3 -
doc-extract-mcp
MCP serversDocument tooling for AI agents: PDF/text reading, chunking, schema-validated JSON output.
-
Keel
MCP serversControl plane MCP that dedups scanner output, rate-limits hosts, and runs non-destructive proofs.
keel-pentest@0.3.0 -
artifact-gauge-mcp
MCP serversLocal build artifact size and dependency weight inspection without file content output. Tools...
artifact-gauge-mcp@1.0.7 -
prompt-protection
MCP serversScan prompts, tool definitions and model output for injection, and guard agent tool calls.
prompt-protection@4.4.0 -
sealkeep
MCP serversLet AI agents use secrets without seeing them: inject into a command, redact the output.
@munhq/sealkeep@0.5.4 -
litellm-mcp
MCP serversGive AI agents access to 100+ LLMs. Call any model, compare outputs.
litellm-mcp@1.0.1 -
vscode-terminal-mcp
MCP serversExecute commands in visible VSCode terminal tabs with output capture and session reuse.
vscode-terminal-mcp@0.1.0 -
mcp-server
MCP serversSign AI output for EU AI Act + FRE 902 compliance, verify content authenticity provenance
@certnode/mcp-server@1.2.2 -
pdf-report-generator
MCP serversGenerate professional PDF reports from LLM output — cover, TOC, tables, charts, 5 themes.
@ctalasila/pdf-report-generator@1.0.1
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.