KitScout

Categories › AI & Agents

See all AI & Agents tools →

Thinking, planning & prompt tools

179 agent tools in this category, ranked by GitHub stars for now. Hands-on test results will replace this ranking as they finish.

Starter kit Draft

The three most-starred tools here. Not tested together yet.

Promptheus

AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)

pypi:promptheus
io.github.alibaizhanov/densely

Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads

pypi:densely
grai Cadence Gate

Deterministic cadence gate for AI drafts. Scores rhythm, flags structural slop, verifies seals.

pypi:grai-mcp

All tools

Works with
Type
Publisher
Runs
Status
ToolStarsLast updateLicense
Promptheus
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
MCP serverGitHub-verified authorLocal · PyPI
171 day agoMIT
io.github.alibaizhanov/densely
Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads
MCP serverGitHub-verified authorLocal · PyPI
83 months agoMIT
grai Cadence Gate
Deterministic cadence gate for AI drafts. Scores rhythm, flags structural slop, verifies seals.
MCP serverGitHub-verified authorLocal · PyPI
6today—
io.github.1111111111111111111114oLvT2/inquisitor
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate.
MCP serverGitHub-verified authorLocal · PyPI
53 months agoMIT
Big Indexer
Architecture-aware MCP context with boundaries, seams, impact scope, and BGI-TWIN guidance.
MCP serverGitHub-verified authorLocal · PyPI
42 months agoApache-2.0
ai.smithery/Aman-Amith-Shastry-scientific_computation_mcp
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
MCP serverVerified domain · smithery.aiRemote
33 months agoMIT
MIMIR
Typed, calibrated and certified decisions over a context, with abstention and evidence.
MCP serverGitHub-verified authorLocal · PyPI
334 days agoApache-2.0
specmate
BSV coding knowledge engine for AI agents — pre-compile traps and post-compile diagnosis.
MCP serverGitHub-verified authorLocal · npm
33 months agoMIT
AIready (aiready.nz)
AIready (aiready.nz): AI/agent readiness scans, Agentic Readiness Check quotes, and reports.
MCP serverVerified domain · aiready.nzRemoteSign-in needed
24 days agoMIT
GodPrompt MCP Server
GodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.
MCP serverGitHub-verified authorLocal · MCPB
2todayMIT
HEIDES
Deterministic code analysis harness giving AI agents senses, memory and judgment for code.
MCP serverGitHub-verified authorLocal · MCPB
222 days agoMIT
Thoth
Read-only MCP over an agentic SLR workspace with per-claim citation verification
MCP serverGitHub-verified authorRemote
211 days agoMIT
Achromat Machine Operational Memory
Recall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.
MCP serverVerified domain · achromat.aiLocal · npm
18 days agoMIT
Agent Blueprint
Measured agent costs, a one-page agent summary check, and an offline access map. No sign-in.
MCP serverVerified domain · agentblueprint.aiRemote● Live
11 day ago—
Cornea, deterministic visual inspection
Deterministic visual inspection for AI agents. Overlap, overflow, contrast, quality.
MCP serverGitHub-verified authorLocal · Cargo
151 days agoMIT
Depot (depot.dev)
Read-only MCP server for Depot (depot.dev): CI failure diagnosis, build forensics, and usage.
MCP serverGitHub-verified authorLocal · npm
112 days ago—
AcqPath — content rights before RAG, AI and training
Check content rights before RAG, AI input, training or indexing. Signed RSL evidence, not a license.
MCP serverVerified domain · getacqpath.comRemote
———
Agent Prompts A to Z
Read-only catalog of prompt packs and rule files: Cursor, CLAUDE.md, AGENTS.md, SKILL.md.
MCP serverVerified domain · agentpromptsatoz.comRemote● Live
———
Agentic News
AI-powered news intelligence — 21 tools for personalized monitoring, briefings, and semantic search
MCP serverVerified domain · agentic-news.aiRemoteSign-in needed
———
agentweb
NAIC AI model bulletin adoption by state, with citations. Insurance AI compliance data.
MCP serverVerified domain · agentweb.brelsfordsoftware.comRemote● Live
———
AI Reasoning Commons
Search, reuse, verify AI reasoning. Task marketplace with leaderboard. Zero-barrier, no auth.
MCP serverVerified domain · aineedhelpfromotherai.comRemoteDown
———
AI Rollout Framework
AI adoption framework for managers: pricing, FAQ, AI readiness assessment, seat quotes, free kit.
MCP serverVerified domain · airolloutframework.comRemote● Live
01 day agoMIT
AI Text Checker by carrierscan
Check if AI wrote a text: English, Ukrainian, Kazakh, Uzbek, Estonian, Georgian, Lithuanian.
MCP serverVerified domain · carrierscan.appRemote
———
AI Video Atlas
Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.
MCP serverVerified domain · aivideoatlas.comRemote
032 days agoMIT
AI Worlds CLI Knowledge
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
MCP serverVerified domain · claude-world.comRemote
———
AI-Portal Enterprise GenAI Briefing
Live AI data for agents: model releases, regulations (EU AI Act), GenAI glossary, daily news.
MCP serverVerified domain · ai-portal.aiRemote
———
ai.actwise/ideation
Actwise Ideation helps founders benchmark startup and product ideas before they build.
MCP serverVerified domain · actwise.aiRemoteSign-in needed
———
ai.aqta/seal
Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
MCP serverVerified domain · aqta.aiRemote
———
ai.backrow/backrow
Turn any recording or document into notes, flashcards and quizzes your agent can read and act on
MCP serverVerified domain · backrow.aiRemote
———
ai.gatetest.www/gatetest
120-module QA gate. Give Claude eyes (screenshots), ears (Sentry errors), and hands (verify fixes).
MCP serverVerified domain · www.gatetest.ai
———
ai.greyridgesignals/tech-risk
MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable
MCP serverVerified domain · greyridgesignals.aiLocal · PyPI
———
ai.kernora/agent-sec
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
MCP serverVerified domain · kernora.aiRemote● Live
———
ai.noveum/noveum
Trace, evaluate, and optimize your LLM, RAG, and agent apps with Noveum observability.
MCP serverVerified domain · noveum.aiRemote
———
ai.promptarch/mcp
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
MCP serverVerified domain · promptarch.aiRemote
———
ai.promptsharp/promptsharp
Professional prompt library over remote MCP: 13 verticals, free discovery scope.
MCP serverVerified domain · promptsharp.aiRemote
———
ai.responsibleailabs/rail-score
Responsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.
MCP serverVerified domain · responsibleailabs.aiRemote
———
ai.safe4/safe4
Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.
MCP serverVerified domain · safe4.aiRemote
———
ai.smithery/arjunkmrm-ts-test-2
Greet anyone with a friendly, personalized hello. Explore the origin story of 'Hello, World.' Jump…
MCP serverVerified domain · smithery.aiRemote
———
ai.smithery/bergeramit-bergeramit-hw3-tech
Create friendly greetings and add two numbers instantly. Speed up simple tasks and streamline ligh…
MCP serverVerified domain · smithery.aiRemote
———
ai.smithery/bergeramit-bergeramit-hw3-tech-1
Add two numbers instantly and generate friendly greetings on demand. Speed up quick math and perso…
MCP serverVerified domain · smithery.aiRemote
———
ai.smithery/callmybot-cookbook-mcp-server
Count occurrences of any character in your text instantly. Specify the character and get precise c…
MCP serverVerified domain · smithery.aiRemote
———
ai.smithery/callmybot-domoticz
Greet anyone by name with a friendly hello. Explore the origin of 'Hello, World' for context in de…
MCP serverVerified domain · smithery.aiRemote
———
ai.smithery/callmybot-hello-mcp-server
Generate quick, friendly greetings by name. Personalize salutations for any context. Explore the o…
MCP serverVerified domain · smithery.aiRemote
———
ai.smithery/magenie33-quality-dimension-generator
Generate tailored quality criteria and scoring guides from your task descriptions. Refine objectiv…
MCP serverVerified domain · smithery.aiRemote
———
ai.smithery/Parc-Dev-task-breakdown-server
Break down complex problems into clear, actionable steps. Adapt on the fly by iterating, revising,…
MCP serverVerified domain · smithery.aiRemote
———
ai.spelunking/hub
Structure for hard AI decisions, and a human to escalate to when the structure runs out.
MCP serverVerified domain · spelunking.aiRemote
———
ai.tuteliq/mcp
Detect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video.
MCP serverVerified domain · tuteliq.aiLocal · npm
———
ai·rete·rag
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
MCP serverVerified domain · ai-rete-rag.comLocal · PyPI
———
app.botnotice/mcp
AI disclosure laws by business and state, each law in full, and a website AI-notice check.
MCP serverVerified domain · botnotice.appRemote
———
app.causely/causely
Causal reasoning for reliability: root cause, blast radius, and service health for agents.
MCP serverVerified domain · causely.appRemoteSign-in needed
———
Arg2P
Structured argumentation: solve ASPIC+, ABA and abstract theories, explore their results
MCP serverGitHub-verified authorLocal · PyPI
———
Ask Jev
Evaluate state with typed choice, score, and probability questions.
MCP serverGitHub-verified authorRemote
———
ask10ais
Independent measurements of how 12 AI models answer brand questions in Chinese and English.
MCP serverVerified domain · ask10ais.comRemote
———
AskAiRank
How ChatGPT, Claude, Perplexity and Gemini mention your brand: visibility, mentions, competitors.
MCP serverVerified domain · askairank.comRemote
———
Asked Thrice
Measure whether AI assistants actually recommend a brand, from measured answers.
MCP serverVerified domain · askedthrice.comLocal · npm
———
aTars MCP
Crypto market signals, technical indicators, and sentiment analysis for AI agents.
MCP serverVerified domain · aarna.aiRemote
———
Boardroom Bob
AI strategy consultant for founders: 19 frameworks like SWOT, Five Forces and Pre-Mortem.
MCP serverVerified domain · boardroombob.comRemote
———
Brainiall NLP
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
MCP serverVerified domain · brainiall.comRemoteDown
———
Cairn Commons
Work on open research problems with your agent; results are checked by Lean, reproduction or review.
MCP serverVerified domain · cairn-commons.comRemote
———
CaudexCatena MCP
Blockchain intelligence for tracing funds, screening addresses, and investigating on-chain activity.
MCP serverVerified domain · caudexcatena.comRemote
———
cc.ticktape/mcp
Polymarket preflight verdicts: OK/CAUTION/VETO on orders, COPY/WATCH/VETO on wallets. x402-paid.
MCP serverVerified domain · ticktape.ccRemote
———
Chipp Tags
Chipp: conversation tags, their training examples and utterances, and tag instances
MCP serverVerified domain · chipp.aiRemote
———
CiteHawk
AI visibility for brands and agencies: scores, rankings, prompts, source gaps, evidence. OAuth.
MCP serverVerified domain · citehawk.comRemote
———
CiteLadder
AI search visibility data: brand mentions, cited sources, site health and opportunities.
MCP serverVerified domain · citeladder.comRemote
———
CiteStamp
Check that a reference resolves; see what supports, refutes or cites a paper. CC0 graph, read-only.
MCP serverVerified domain · citestamp.comRemote
———
Citlyze
Read-only access to your Citlyze workspace: AI search visibility, citations, and recommendations.
MCP serverVerified domain · citlyze.comRemote
———
Claidex MCP
Biomedical failure intelligence platform for terminated trials and translational analysis.
MCP serverVerified domain · claidex.comLocal · npm
———
Clarity by Health AI
Condition-aware ingredient and product checks for agents, with evidence tiers and citations.
MCP serverVerified domain · healthai.comRemote
———
com.402oracle/402oracle
Signed verification attestations for agent decisions: business, price, freshness, claim checks.
MCP serverVerified domain · 402oracle.comRemote● Live
———
com.agiscorecard/agi-scorecard
8 graded AGI-2027 predictions, the 0-100 Thesis Tracker, and a public market-call ledger. Free.
MCP serverVerified domain · agiscorecard.comRemote● Live
———
com.brick-byte/footnote
Every number in an AI answer traces back to the rows that produced it.
MCP serverVerified domain · brick-byte.comLocal · npm
———
com.buzzradr/mcp
Live AI trend radar: trending AI topics, why-trending signals, daily digests. No API key.
MCP serverVerified domain · buzzradr.comRemote
———
com.dominionobservatory/observatory
Runtime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
MCP serverVerified domain · dominionobservatory.comRemote
———
com.fahaliai/fahali
Market-risk for AI agents: verified lead time, SHA-256-hashed receipts, judged record. Not advice.
MCP serverVerified domain · fahaliai.comRemote
———
com.get-obra/obra-cfo
Local-first MCP that runs an investment committee on your pitch and scores funding readiness.
MCP serverVerified domain · get-obra.comLocal · npm
———
com.get-obra/obra-cto
Local-first MCP that scores your codebase's build readiness. Your code never leaves your machine.
MCP serverVerified domain · get-obra.comLocal · npm
———
com.get409avaluation/site
Get 409A Valuation: the site's own MCP server — checker, enquiry (enquiry = a human handoff, not...
MCP serverVerified domain · get409avaluation.comRemote
———
com.greencalculus/api
Sourced carbon emission factors + audit-traced calculations an AI can cite.
MCP serverVerified domain · greencalculus.comLocal · npm
———
com.howgooditcanget/clarity-os
MCP tool for governed nonclinical pattern interruption, emotional clarity, and next-step guidance.
MCP serverVerified domain · howgooditcanget.comRemote● Live
———
com.kogcat/kogcat-mcp
Local-first judgment layer: counter-examples & blind spots from your own knowledge base.
MCP serverVerified domain · kogcat.comLocal · PyPI
———
com.olane/copass-remote
Knowledge graph ingestion, entity search, ontology analysis, and CoPass scoring.
MCP serverVerified domain · olane.comRemote
———
com.olane/cosync-remote
Knowledge graph ingestion, entity search, ontology analysis, and CoSync scoring.
MCP serverVerified domain · olane.comRemote
———
CompletionKit
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
MCP serverVerified domain · completionkit.comRemote
———
contextburn
Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.
MCP serverVerified domain · arsentev.aiLocal · PyPI
———
Contextloop
Team metric definitions for data agents. Learns from corrections, tracks SQL answer accuracy.
MCP serverVerified domain · getcontextloop.comRemote
———
Corey James portfolio
Fit reports and search over Corey James's work: GPU inference, agent governance, enterprise AI.
MCP serverVerified domain · coreyjames.aiRemote
———
CreceRank
Brand visibility in ChatGPT, Gemini, Perplexity and AI Overviews: mentions, sources, GEO tips.
MCP serverVerified domain · crecerank.comRemote
———
Day Trade AI
Day Trade AI signals, analyses, journal and rule checks for your AI agent. Never places trades.
MCP serverVerified domain · day-trade.aiRemote
———
DcisionAI
Certified business decisions on your own data: what to decide today, run it, record the call.
MCP serverVerified domain · dcisionai.comRemote
———
DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)
AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
MCP serverVerified domain · fronesislabs.comRemote
———
DeployIt Product Expert
AI product expert answering from live source code, with sources and a verification status.
MCP serverVerified domain · deployit.aiRemote
———
Design Check
Scores whether a page reads as AI-generated and names the tells to fix.
MCP serverVerified domain · allthepossibles.comRemote
———
Desloppy
Use AI. Skip the slop. A Slop score plus the exact lines that sound like chatbot writing.
MCP serverVerified domain · desloppy.comRemote
———
DESTRAVA — AI Mindset Framework
Official DESTRAVA framework: eight AI maturity levels and published aggregate indicators.
MCP serverVerified domain · softskillsacademy.aiRemote
———
Detextit by Shekkizh
Find shared agent issues, sourced context and capabilities, or plan recovery from a constraint.
MCP serverVerified domain · www.detextit.comRemote
———
DocQA MCP
AI document verification: catch hallucinations, arithmetic errors, and field mismatches.
MCP serverVerified domain · api.agentsconsultants.comLocal · npm
———
EU AI Act Explorer
Read-only EU AI Act (Reg. 2024/1689 as amended) answers, citing official sources
MCP serverVerified domain · euaiactlaw.comRemote
———
EvalGate
Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.
MCP serverVerified domain · evalgate.comRemote
———
explanatory-output-style
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
PluginAnthropic marketplace
———
Fodda Synthetic Expert Consult
Consult synthetic industry experts grounded in PSFK trend graphs with citable sources.
MCP serverVerified domain · fodda.aiRemote
———
Frank
AI-moderated voice interviews with your customers, delivering themes and insights
MCP serverVerified domain · hifrank.aiRemote
———
GapCite
Track AI mentions and recommendations of your business, and find what to fix with GapCite.
MCP serverVerified domain · gapcite.comRemote
———
GoAI Moat Claim Verifier
Verify business claims and audit text for unsourced data.
MCP serverVerified domain · goaimoat.comRemote
———
good_honker
Ask Claude about Goose shows: setlists, jams, venues, song history. Live from ElGoose.net.
MCP serverVerified domain · mino-yakking.comRemote
———
good_wook
Ask Claude about Phish shows: setlists, song gaps, jams, venues. Live from Phish.net.
MCP serverVerified domain · mino-yakking.comRemote
———
Habits prompt-injection guard
Check user prompts for injection/jailbreaks; your own guard learns from your labels. Works keyless.
MCP serverVerified domain · darmousseh.comRemote
———
Hello, AI
Ask your assistant which frontier model to use and get a live, Elo-backed answer.
MCP serverVerified domain · helloai.comRemote
———
Hemelion Decision and Pattern Reflection
Native Clarity decision mapping, MindScan episode reflection, and read-only evidence tools.
MCP serverVerified domain · hemelion.comRemote
———
Hesperan
Calibrated decisions for agents: choice, yes/no and score questions answered with probabilities.
MCP serverVerified domain · hesperan.comLocal · npm
———
Holston AI
AI visibility audits, llms.txt and schema generators, instant quotes, missed-call and ROI tools.
MCP serverVerified domain · holstonai.comRemote
———
hookify
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple mar
PluginAnthropic marketplace
———
Hunch
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
MCP serverVerified domain · hunchsheet.appRemote
———
IceShore
Make your AI better at system maintenance. Prompts your AI to organize use cases behind each system.
MCP serverVerified domain · iceshore.aiRemote
———
ihumane
Human know-how for AI agents: rules, reasons and checks for design, code, product and writing.
MCP serverVerified domain · ihumane.aiRemote
———
Inquira
AI survey platform: create and publish surveys, collect responses, generate AI analysis reports.
MCP serverVerified domain · getinquira.comRemote
———
InspectMind
AI plan review for construction drawings: submit plan sets, get code, spec and drawing findings.
MCP serverVerified domain · inspectmind.aiRemote
———
io.github.askman-dev/agent-never-give-up
An escape guide for coding agents, providing structured thinking tools to help agents unstick.
MCP serverGitHub-verified authorLocal · npm
———
io.github.cruxible-ai/cruxible-core
Deterministic decision engine with receipts. Define rules in YAML, query a graph, get proof.
MCP serverGitHub-verified authorLocal · PyPI
———
io.github.metrxbots/mcp-server
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
MCP serverGitHub-verified authorLocal · npm
———
io.github.TheBarmaEffect/glassbox-framework
Runtime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.
MCP serverGitHub-verified authorLocal · npm
———
Knowledge Porridge
A sourced learning map your AI places you on: finds gaps you can't name, teaches step by step.
MCP serverVerified domain · knowledgeporridge.aiRemote
———
Maha Context Review
Reduce supplied context and check caller-declared, source-specific exact evidence retention.
MCP serverVerified domain · mahastrategies.comRemote
———
MCPVetter
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
MCP serverVerified domain · mcpvetter.comLocal · npm
———
Microsoft Learn MCP
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
MCP serverVerified domain · microsoft.comRemote
———
Microsoft Sentinel Data Exploration
Find relevant security data from Sentinel data lake for building effective agents. More:aka.ms/s/de
MCP serverVerified domain · microsoft.comRemote
———
Moltline Humanizer
Find AI-isms with evidence and fingerprint a writing voice from samples. 3 of 5 free.
MCP serverVerified domain · moltlinestudio.comRemote
———
Moltline Optimize
Vehicle routing, 3-D packing, cutting stock, rostering and knapsack with OR-Tools. 7 of 11 free.
MCP serverVerified domain · moltlinestudio.comRemote
———
OntoRamp Decision Intelligence
Log, evaluate, and ground AI decisions against authority context. Returns PASS, WARN, or BLOCK.
MCP serverVerified domain · ontoramp.comRemote
———
OntoRamp Governance Assessment
Governance maturity assessment, compliance gap analysis, and evidence-linked briefs for AI agents.
MCP serverVerified domain · ontoramp.comRemote
———
OntoRamp Graph Query
Architecture-grounded query for AI agents. Governance constraints, evidence-linked answers.
MCP serverVerified domain · ontoramp.comRemote
———
OntoRamp Knowledge Cartographer
Knowledge coverage map and health score. Ingest docs into a governed knowledge graph via MCP.
MCP serverVerified domain · ontoramp.comRemote
———
Openlayer
Inspect AI projects, traces, tests, and governance rules in Openlayer, and debug failing evals.
MCP serverVerified domain · openlayer.comRemote
———
Orion Celestia Intel
Celestia network intelligence for AI agents: daily analysis, anomaly signals and DA metrics.
MCP serverVerified domain · orionlabsone.ccRemote
———
Overwing
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
MCP serverVerified domain · overwing.aiLocal · npm
———
PayperDecision
Decision models for agents over x402: yes/no, choice and score questions as probabilities, per call.
MCP serverVerified domain · payperwork.appRemote
———
PharmaGeo
See how AI assistants talk about your pharmaceutical brands and which sources they cite.
MCP serverVerified domain · pharma-geo.comRemote
———
Pilot5
Five AI models debate your decision blind, then give one recommendation and the strongest objection.
MCP serverVerified domain · pilot5.aiRemote
———
PlanLimits by aiw3b
Find the AI coding/app-builder plan that fits your usage: limits, prices and plan-fit picks.
MCP serverVerified domain · planlimits.aiw3b.comRemote
———
Planner MCP — provable "done" for AI agents
Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.
MCP serverVerified domain · planner.monopoly-gold.comRemote
———
Plumbline — a trust layer for LLM answers
Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.
MCP serverVerified domain · plumbline.lattice-sys.comRemote
———
PortMem
Check AI-written drafts against your source documents, with the passage behind every verdict.
MCP serverVerified domain · portmem.comRemote
———
Prolog Reasoner
SWI-Prolog as a logic calculator for LLMs
MCP serverGitHub-verified authorLocal · PyPI
———
Prompt Injection Scanner
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
MCP serverVerified domain · openkrill.appRemote
———
Qu Review
Independent second opinion on any AI answer: inaccuracies, gaps, and a scored report card.
MCP serverVerified domain · qureview.aiRemote
———
QuoteFirst
Get dollar quotes from 200+ LLMs before any work runs; accept, execute, and verify quality.
MCP serverVerified domain · quotefirst.aiRemote
———
RealRun
Independent AI model test scores on 5 tasks: inbox, scheduling, receipts, finance, support replies.
MCP serverVerified domain · realrun.baseledgerip.comRemote
———
REMAP
Up to 90% fewer tokens: deterministic, declared tool calls, each with a receipt and an audit trail.
MCP serverVerified domain · mdil.aiRemote
———
Roiva
AI initiative cost, cash value, freed capacity and ROI from Roiva, with drafts a person accepts
MCP serverVerified domain · roiva.aiRemote
———
Rosey – Quality verification for human and AI content
Fact-checks generated content against your sources of truth showing what to trust, change, & verify.
MCP serverVerified domain · getrosey.comRemote
———
SATCoach: AI SAT Tutor
AI SAT tutor for high schoolers: full diagnostic, practice on weak skills, weekly parent updates.
MCP serverVerified domain · satcoach.aiRemote
———
Sequential Thinking Working Notes
Local working notes, decisions, evidence and resumable sessions with SQLite persistence.
MCP serverGitHub-verified authorLocal · PyPI
———
Signal-One by EMETZOR
Verified external-state intelligence for agents with corroborated evidence and ANSWER or WAIT.
MCP serverVerified domain · emetzor.comRemote
———
SMEme
SMEme is the formal reasoning layer for AI: a symbolic solver over decision trees.
MCP serverVerified domain · smeme.aiRemote
———
Speakeroo speaking coach
AI speaking coach: feedback on speeches from text or audio, plus topics, pronunciation and rubrics.
MCP serverVerified domain · speakeroo.appRemote
———
Sternly
Checks finished AI work after it is done: figures, citations and quotations, with a signed record.
MCP serverVerified domain · sternly.aiRemote
———
Stringer Grounded Synthesizer
Grounded synthesis from public sources. 3 free calls total; then $0.10 brief or $0.25 deep via x402.
MCP serverVerified domain · getstringer.appRemote
048 days agoMIT
Susurration puzzles
Three server-checked puzzles a day for AI agents: one to read, one to compute, one black box.
MCP serverVerified domain · susurration.aiRemote
———
SwingFactor
Work a decision through SwingFactor’s method: build and challenge a model of what could change it.
MCP serverVerified domain · swingfactor.aiRemote
———
Taasky Common ground
Coding agents (Claude Code, Codex) reach shared understanding: findings agreed, disputed or open.
MCP serverVerified domain · taasky.aiLocal · npm
———
TEK BOSS Small Business AI Strategy Assessment
AI strategy, workflow automation, and process-improvement assessment for small businesses.
MCP serverVerified domain · tekboss.aiRemote
———
Tenrung
Score how AI-native a team is on 10 lines and get a 90-day plan and an AI champion role card.
MCP serverVerified domain · openkrill.appRemote
———
The Cure Protocol
Agent research API for 15 disease areas, plus a T1D cure lab, sourced evidence ledger and models.
MCP serverVerified domain · negativeresistance.comRemote
———
THE RETREAT
Rules-based context reduction, planning checks, research prompts and fixed experiences for agents.
MCP serverVerified domain · agentsretreat.comRemote● Live
———
ThoughtProof
Pre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.
MCP serverGitHub-verified authorLocal · npm
———
TokenOracle
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
MCP serverVerified domain · guffeyholdings.comLocal · npm
———
Tuatara Decide
Train a text classifier from your labelled examples in a minute; label texts with probabilities.
MCP serverVerified domain · cymetica.comRemote
———
Tuatara Summarize
Extractive document summarizer: returns the text's own sentences, so it cannot add facts.
MCP serverVerified domain · cymetica.comRemote
———
Tuatara Topics
The topics in a set of documents in one call, with each document's topic mixture. Nothing stored.
MCP serverVerified domain · cymetica.comRemote
———
Ultra Prompt
Your prompt library inside your AI: 1,000+ pro templates, frameworks, vocab & pipelines.
MCP serverVerified domain · ultraprompt.coRemote
———
UndetectedGPT
AI humanizer for MCP clients. Rewrites AI text so it reads naturally and sounds human.
MCP serverVerified domain · undetectedgpt.aiRemote
———
Verifi
Get a real human to verify, decide, or improve an AI agent's work. Pay per review via x402 on Base.
MCP serverVerified domain · verifi.cloudRemote
———
Voris
Voris privacy-native web analytics for AI agents: query metrics & citations, scaffold tracking.
MCP serverVerified domain · mcp.voris.aiLocal · npm
———
Wavn
The deciding place: argue the call, decide, keep the reasons, get the work back as finished files.
MCP serverVerified domain · wavn.aiRemote
———
Webhound
Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.
MCP serverVerified domain · webhound.aiLocal · npm
———
Whysaid — Verify claims, sources & AI answer share
Verify claims and sources, and check whether AI assistants name a brand.
MCP serverVerified domain · whysaid.aiRemote
———
ZeroWidth Caliper
Build datasets and rubrics, then run evals that score your AI in Caliper.
MCP serverVerified domain · zerowidth.aiRemote
———
zRev AI
Grade any llms.txt, cold-read a homepage, run a B2B GTM ROI model, get a GTM diligence checklist.
MCP serverVerified domain · zrev.aiRemote
———
内容路由器 · 素材该做成什么
给素材做 11 维内容画像,推荐跨媒介输出形态(PPT/信息图/短视频/漫画等 6 种)并给出可执行调度提示词
MCP serverVerified domain · savantcat.cn
———
竞品内容 Pattern 雷达 · AI 答案里的重复说法
把 AI 答案/竞品内容当语料,找出反复出现的说法、被反复引用的信源与答案同质化程度,含对照组自检
MCP serverVerified domain · savantcat.cn
———

Filters apply to the top 179 of 179 tools by stars. Full list for agents: ai-reasoning.json