Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Crawdar Business Research
MCP serversEvidence-backed public business research for agents with compact, pageable output.
-
mcp
MCP serversThe output layer for AI agents: turn what an agent produced into a finished file.
@bigapi/mcp@0.9.1 -
stylemcp
MCP serversBrand rules for AI outputs. Validate and rewrite text to match your brand voice.
stylemcp@0.1.4 -
Image Resize API
MCP serversResize images from URL — PNG, JPEG, WebP output. x402 micropayment.
-
github
MCP serversMCP server for GitHub operations (PRs, issues, actions) with structured, token-efficient output
@paretools/github@0.7.1 -
python
MCP serversStructured Python tool output (ruff, mypy, pip-audit, pip-install) as typed JSON.
@paretools/python@0.8.0 -
Tkach Security
MCP serversFail-closed MCP adapter for untrusted model output over a local Tkach runtime.
tkach-mcp@0.1.2 -
NinFenz Content Gate
MCP serversAI output assurance with versioned contracts, deterministic release gates and reproducible evidence.
ninfenz@1.1.2 -
perf-mcp
MCP serversFact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
perf-mcp@0.1.1 -
haltproof
MCP serversFail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.
haltproof-cli@0.1.3 -
signato
MCP serversLocal confidentiality chamber: blocks the wrong AI output before it leaves the machine.
signato@0.13.1 -
agent-immune
MCP serversAI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
agent-immune@0.2.2 -
keyshroud
MCP serversAgent-safe secrets (local encrypted vault or Vaultwarden): injected into commands, masked in output
keyshroud@0.12.1 -
Rowbase
MCP serversSafe, read-only-by-default MySQL, PostgreSQL & SQLite access for AI agents. TOON output.
rowbase-db@0.3.0 -
Distil
MCP serversReversibly compress tool outputs to recoverable handles; expand to exact original bytes on demand.
distil-llm@1.30.0 -
AISchemaGate and DataContractGate
MCP serversAISchemaGate validates and repairs structured LLM output against a contract, plus DataContractGate.
@nightmoose/contractgate-mcp-server@0.4.1 -
vecline
MCP serversLocal-first image, vector and document toolkit that measures its own output. Nothing uploaded.
vecline@2.1.4 -
LLMVerify
MCP serversLocal-first MCP server for LLM output verification — risk signals, injection and PII checks.
llmverify@1.8.0 -
Tokenscope
MCP serversAnalyze Claude Code session cost & context attribution: output, cached re-reads, cache writes.
@wartzar-bee/tokenscope-mcp@0.2.3 -
riskoracle
MCP serversRiskOracle - 13-tool enterprise risk MCP: heatmaps, KRIs, scenario sims, Basel/ICAAP outputs.
-
keelyard
MCP serversProof gate, undo and output trimming for Claude Code, Codex and OpenCode coding agents.
keelyard@1.2.1 -
evalsnap
MCP serversSnapshot diff for agent and tool outputs: changed cases, score regressions, pass/fail verdict.
@reneturcios/evalsnap@0.1.0 -
wattindex
MCP serversGPU energy per million output tokens by model and GPU, with grid carbon intensity.
@reneturcios/wattindex@0.1.0 -
Invoance
MCP serversRecord signed events, AI outputs and document fingerprints, and check any record later.
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.