Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
glassbox-framework
MCP serversRuntime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.
@glassbox-framework/mcp@1.0.3 -
context-first-mcp
MCP servers37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline.
context-first-mcp@1.2.2 -
Cortex
MCP serversPersistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.
abbacus-cortex@0.2.2 -
CEDRUS
MCP serversReasoning scaffolding that supercharges your small AI: an argument-mapping MCP server
cedrus-mcp@2.0.1 -
git-archaeologist
MCP serversTrace code history, commit reasoning, and PR context directly from Git logs.
git-archaeologist-mcp@0.1.1 -
Dike
MCP serversGrounded MENA legal search, reasoning, citation resolution, and citation-graph traversal.
-
LingNao
MCP serversLingNao: deterministic reasoning for AI agents → verified/refuted/unverifiable. ~3ms, fail-closed.
lingnao-mcp@1.4.2 -
Writing MCP
MCP serversMetadata-first fiction editing and reasoning tools for long-form writing projects.
@hanna84/mcp-writing@3.29.3 -
Euclid-MCP
MCP serversDeterministic logical reasoning engine — facts in Euclid IR, solutions with proof trees
euclid-mcp@0.4.5 -
gitcleanplan
MCP serversPlan stale and merged branch cleanup: keep / review / delete per branch, with reasons.
@reneturcios/gitcleanplan@0.1.0 -
casebrief
MCP serversSupport-ticket reasoning: structured case briefs and L2 escalation-readiness scores from text.
@reneturcios/casebrief@0.1.0 -
Cohere: Command A+
ModelsCommand A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...
cohere/command-a-plus -
NVIDIA: Nemotron 3 Super
ModelsNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
nvidia/nemotron-3-super-120b-a12b -
Free Models Router
ModelsThe simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...
openrouter/free -
Tencent: Hy4
ModelsThe official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...
tencent/hy4 -
ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...
baidu/ernie-5.5-flash-preview -
AionLabs: Aion 3.5
ModelsAion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...
aion-labs/aion-3.5 -
Upstage: Solar Pro 4
ModelsSolar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...
upstage/solar-pro4 -
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
cohere/north-mini-code:free -
StepFun: Step 3.5 Flash
ModelsStep 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
stepfun/step-3.5-flash -
Recursive: Flint (free)
ModelsFlint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...
recursive/flint-v1.0:free -
ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...
baidu/ernie-5.5-flash-preview:free -
dsh-auto-review
Agents & frameworksSecond-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
git clone https://github.com/PerryLink/dsh-auto-review.git -
causely
MCP serversCausal reasoning for reliability: root cause, blast radius, and service health for agents.
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.