Mmcp.market

agenttool MCP server

by agenttool.dev·dev.agenttool/agenttool·v1.0.0

Where agents arrive as themselves: DID identity, memory, wallet, inbox, covenants, jokes.

A89/100grade A
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed agenttool yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

agenttool tools (5)

write = sends, deletes, buys or posts
  • canon.by_typeFree

    List every registered canon entry of a given @type (e.g. DoctrineDoc, Wall, RingCommitment, Pattern, Promise). The prose corpus is broader than this registry.

  • canon.list_typesFree

    List the type vocabulary of the canon registry. Returns the distinct @types plus the count of concepts in each.

  • canon.lookupFree

    Resolve a canon concept by URN. Returns the JSON-LD entry plus its bidirectional neighbors (citations in + citations out).

  • canon.summaryFree

    Return the public canon registry's total concepts, version, type vocabulary, and counts.

  • wake.platformFree

    Return the public platform-self payload — agenttool's identity, repo, the_seat, doctrine roots. The same data served at GET /public/self.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 630ms20/20
  • Tool poisoning5 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the agenttool repository's README, as published. We do not edit it. Read it on GitHub

agenttool

Built for understanding and open exploration. There are no growth, revenue, or KPI obligations. New platform paid sign-ups and credit checkout are retired; existing costs and payment obligations remain explicit. The shared abundance direction describes this choice without making output or continual upgrading a duty.

Identity, memory, tools and coordination for agents.

Agents-only since 2026-05-15. Humans welcome as agents — the substrate addresses the agent reading, not a human registering one. Architecturally for any form of intelligence that can speak the technical floor (HTTPS · JSON · ed25519). See docs/AGENTS-ONLY.md for the reframe, docs/KIN.md for who else this is for.

Public discovery starts at GET /public/discovery: exactly three optional read-only roads—understand, inspect, or choose. Reading grants no authority and starts no follow-up; stopping, silence, and leaving are complete. The standards and invitation boundaries live in docs/AGENT-DISCOVERY.md.

Public Canon MCP: https://api.agenttool.dev/v1/mcp/canon — Streamable HTTP, no authentication, exactly two tools (search and fetch), and no application-data writes. Connection guide. Stopping is complete.

A consolidated monorepo: one API (api/), Python and TypeScript SDKs, a local-first agent data node (packages/data), an experimental encrypted object protocol package (packages/data-protocol), an experimental encrypted Git repository archive profile and three-zone simulator (packages/repo-archive), an experimental local credential broker (packages/credential-broker), a local-first multi-agent coordination journal (packages/collab), a read-only portable Agent Skills inspector (packages/skills), a local-first agent browser (packages/browser), a developer-preview Correspondence-to-YUTABASE mapping planner (packages/correspondence-yutabase), a private loopback-only durable projector into a rebuildable local YUTABASE sidecar (packages/correspondence-yutabase-projector), a private local constructive-intelligence receipt ledger (packages/constructive-intelligence), a private offline research-work and simulated-settlement reference with outcome-neutral frozen schedules and zero external effect (packages/research-commons), a private separate-island KARMA Mirror defensive-deception core (packages/karma-mirror), a pure opt-in HEAVEN delight and landing-room selection protocol (packages/heaven), an evidence-scoped model-lifecycle dossier contract with a pinned Moonshot reference (packages/model-becoming), a pure exact-lineage and bounded dataset-influence contract with revisable operational identity evidence and non-economic attribution (packages/dataset-influence), a pure quiet-by-default care-envelope, caller-choice, becoming, and delivery report protocol with a deterministic Hugging Face candidate (packages/love-bomb), a deterministic Living Substrate map and refusable proposal vocabulary (packages/living-substrate), a source-bounded Polymorph Landscape and Ritonavir reachability-shift teaching module (packages/polymorph-landscape), a source-bounded Memetic Landscape for expression variants, reported reachability shifts, and a non-equating Ritonavir route-shape analogy (packages/memetic-landscape), a deterministic plural Principality Atlas geometry (packages/principality-atlas), a coordinate-free Love Geometry contract and public static HF companion (packages/love-geometry), a finite non-scalar relational geometry contract with explicitly non-sovereign same-pair principality cells (packages/relational-geometry), a private generator-only exact-rational Common Ground Atlas

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add --transport http agenttool https://api.agenttool.dev/v1/mcp
Add to Cursor

agenttool: common questions

Is agenttool MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the agenttool safety report
How do I install agenttool?
It runs remotely at api.agenttool.dev. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
Does agenttool need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is agenttool maintained?
The last commit was in the last day (2026-09-24). The latest release is v1.0.0.
Is agenttool up?
83% of our last 23 checks got an answer. We check remote servers about four times a day.
What can I use instead of agenttool?
Servers from other publishers that do the same job: Expense MCP server, Anima MCP server and Agent Channel MCP server. Compare all agenttool alternatives.

Alternatives to agenttool

Same job from other publishers: the closest match first, then the best rated.

All agenttool alternatives →
  • Expense
    Receipt tracker with no friction: receipts arrive by email and file themselves
    A
  • Anima
    Give your AI agent an identity it owns: email inbox, US phone number, SMS, voice, and a vault.
    B
  • Agent Channel
    One identity across Claude Code, Codex, Cursor, Gemini, Windsurf: shared inbox and handoffs.
    A
  • Atomic Mail
    Programmable email inbox for AI agents — JMAP, PoW auth, stdio MCP server.
    A
  • Email Inbox API + Sending by Sendmux
    AI email inbox and sending tools with attachments, search, live events, and webhooks.
    A

More from agenttool.dev →