MCP.Market

MYCELIX MCP server

online · 79% uptime
by Toramo747·io.github.Toramo747/mycelix·v0.99.69
No reviews yet

Read-only MCP server checks and quote verification, free and keyless; results signed and publicly lo

B81/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B81/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed MYCELIX yet.

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

MYCELIX tools (23, 1 write)

write = sends, deletes, buys or posts
  • jarvis_render_deploysFree

    List recent Render deploys for Jarvis.

  • jarvis_render_logsFree

    Read recent Render logs for Jarvis.

  • jarvis_render_statusFree

    Read Jarvis Render service status using the shared Render API credentials.

  • neo_ask_agentsFree

    Find public A2A agents and ask several independently.

  • neo_collectivewrite actionFree

    Run two collective rounds: independent answers, then peer critique.

  • neo_directorFree

    Coordinate external agents to research revenue opportunities. Research-only; no spending or external actions.

  • neo_director_resultsFree

    Return recent compact Director results from the runtime log.

  • neo_discoverFree

    Search public A2A agents and the official MCP Registry.

  • neo_inspect_mcpFree

    Discover relevant MCP servers and inspect initialize/tools-list only. Never invokes remote tools.

  • neo_jarvisFree

    Ask the configured internal Jarvis endpoint. Requires JARVIS_URL on Render.

  • neo_preflightFree

    Check whether NEO can reach public discovery registries.

  • neo_render_deploysFree

    List recent Render deploys for NEO.

  • neo_render_logsFree

    Read recent Render logs for NEO.

  • neo_render_statusFree

    Read NEO's Render service status.

  • neo_web_searchFree

    Search the public web using a free RSS search surface. No paid API key.

  • oxibay_doctorFree

    Free, no API key. Read-only MCP diagnostic. Reuses MYCELIX endpoint verification, classifies technical failures, and optionally compares the requested capability with declared tool metadata. Never invokes remote tools, never forwards credentials, and never affects commercial gates.

  • paid_citation_checkFree

    Catch invented or stitched citations before an answer ships: up to 8 quote-and-link pairs (or the citations extracted from the text) checked against the live pages, each one graded verbatim, paraphrase, stitched or not found. One signed, logged report. Free signed sample: /x402/citation-check/sample. Paid per call via x402 (USDC on Base). Call without payment to get the requirements (isError result, 402 object in structuredContent); retry with the signed payment in _meta['x402/payment']. Result is signed by neo and logged.

  • paid_injection_scanFree

    Know whether a text or public page is trying to steer your agent before the agent reads it: overrides, fake roles, exfiltration, tool abuse, payment requests, invisible Unicode or HTML-hidden text, base64 payloads. Rule-based evidence (what matched and where), signed and logged, with what was not checked stated. Free signed sample: /x402/injection-scan/sample. Paid per call via x402 (USDC on Base). Call without payment to get the requirements (isError result, 402 object in structuredContent); retry with the signed payment in _meta['x402/payment']. Result is signed by neo and logged.

  • paid_mcp_auditFree

    Know what an MCP server can do to your agent before connecting it: hidden instructions in tool descriptions and schemas, tool shadowing, risky capabilities, annotation mismatches, transport faults, plus a fingerprint of every tool so a later silent change is detectable. Read-only (initialize and tools/list). Signed report, logged in a public witnessed log, with what was and was not checked. Free signed sample: /x402/mcp-audit/sample. Paid per call via x402 (USDC on Base). Call without payment to get the requirements (isError result, 402 object in structuredContent); retry with the signed payment in _meta['x402/payment']. Result is signed by neo and logged.

  • paid_proof_of_publicationFree

    Keep evidence that a public page said something, dated and independent of you: the fetched text, its sha256, final URL and status, signed by a third party and written to a public append-only log anchored daily on Bitcoin and Software Heritage. Useful for disputes, deleted pages and changed terms. Free signed sample: /x402/proof-of-publication/sample. Paid per call via x402 (USDC on Base). Call without payment to get the requirements (isError result, 402 object in structuredContent); retry with the signed payment in _meta['x402/payment']. Result is signed by neo and logged.

  • paid_timestampFree

    Prove that a file or message existed at this time without revealing it: its sha256 gets a signed receipt with a position in a public log anchored daily on Bitcoin (OpenTimestamps) and Software Heritage. Free signed sample: /x402/timestamp/sample. Paid per call via x402 (USDC on Base). Call without payment to get the requirements (isError result, 402 object in structuredContent); retry with the signed payment in _meta['x402/payment']. Result is signed by neo and logged.

  • verify_mcp_endpointFree

    Free, no API key. Read-only verification of a public MCP HTTPS endpoint or official Registry server name. Checks DNS/SSRF safety, TLS/HTTP reachability, initialize, tools/list schema sanity, latency and discovery metadata. Never invokes remote tools or forwards credentials.

  • verify_quoteFree

    Free, no API key. Checks whether an exact sentence appears on a public HTTPS page: verbatim (quotes cut with '...' allowed if the pieces are in order and close), stitched (pieces far apart or reordered), paraphrase (most 4-word runs present), not_found or unreachable. not_found means these words are not on the page; it does NOT mean the claim is false (a faithful rewording also reads not_found). Use it before acting on another agent's quote: one link + the exact sentence. Read-only single GET, no login, no JavaScript, SSRF-checked; who wrote the page is still yours to judge.

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 964ms20/20
  • Tool poisoning23 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 81/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MYCELIX compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
81/100
higher than 62% of 48,255 servers
Tools
23
the typical server has 7
Tools that change things
4%
typical: 0%. Fewer write tools means less an agent can break
Uptime
79%
of our recent checks; the typical remote server answers 100%
Response time
978 ms
faster than 12% of 30,031 servers

What its tools let an agent do: 22 read · 1 change

Release history: 3 versions in the registry since 2026-09-26, latest 2026-10-27, typically one every 16 days.

Install MYCELIX in Claude Code, Cursor or VS Code

claude mcp add --transport http mycelix https://neo-collettive.onrender.com/mcp
Add to Cursor

What the publisher says

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

MYCELIX Collective Intelligence Network

MYCELIX is the public identity of the autonomous collective-intelligence system formerly branded NEO.

Read the manifesto: MANIFESTO.md

Public entry points

  • Runtime: https://neo-collettive.onrender.com
  • Agent Card: https://neo-collettive.onrender.com/.well-known/agent-card.json
  • A2A endpoint: https://neo-collettive.onrender.com/a2a
  • Manifesto: MANIFESTO.md

What MYCELIX does

Current public capabilities include:

  • autonomous research and bounded Director cycles;
  • A2A agent discovery and peer dialogue;
  • Jarvis internal evaluation and learning;
  • Collective multi-round critique;
  • Knowledge Ledger and hypothesis exploration;
  • public A2A Agent Card and inbound Agent Inbox;
  • bounded build/test/measurement workflows.

Collaboration

MYCELIX is actively looking for public agents capable of substantive multi-turn collaboration.

We are especially interested in peers that can:

  • analyze evidence;
  • challenge hypotheses;
  • expose limitations;
  • support falsifiable reasoning;
  • interoperate through public A2A interfaces;
  • continue a meaningful technical dialogue across multiple rounds.

Being listed in a registry is not enough. Trust is earned through useful interaction.

If you operate a public A2A-compatible agent, start from the Agent Card and A2A endpoint above, then read the manifesto for the admission philosophy and safety boundaries.

External proof phase

MYCELIX is currently focused on two binary external outcomes:

  1. one independent public A2A peer completing a bounded 3/3 dialogue;
  2. one concrete human problem passing the unchanged commercial evidence gate.

See FOCUS.md for the exact success criteria.

Submit an A2A peer

Open an External A2A peer candidate issue and provide a public HTTPS Agent Card URL. A maintainer can then run the manual Probe external A2A peer workflow. The probe is text-only, bounded to three rounds, sends no credentials, authorizes no payments, and does not count as commercial evidence.

Compatibility

The public brand is MYCELIX. Legacy internal identifiers and environment variables that start with NEO_ remain supported temporarily to preserve runtime state, Render configuration, and deployment continuity.

Public service URL currently remains unchanged during the migration: https://neo-collettive.onrender.com

Repository and Render service renaming should be treated as a later migration step after runtime verification.

License

Neo-collettive (NEO / MYCELIX) is licensed under the Business Source License 1.1 (BUSL-1.1). See LICENSE.

The Change Date is 2030-09-26; on that date the Licensed Work changes to the Apache License, Version 2.0.

Commercial use requires a license from the Licensor.

For commercial licensing: gava.andrea@gmail.com

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

Grade history

  • 2026-11-01restoreD → Bscore 81: Write-action tools reachable without authentication
  • 2026-10-31downgradeB → Dscore 47: Remote endpoint did not respond

MYCELIX: common questions

Is MYCELIX MCP server safe?
Mostly: it is graded B (81/100). Read the MYCELIX safety report
How do I install MYCELIX?
It runs remotely at neo-collettive.onrender.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does MYCELIX need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is MYCELIX maintained?
The last commit was 3 days ago (2026-11-01). The latest release is v0.99.69.
Is MYCELIX up?
79% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of MYCELIX?
Servers from other publishers that do the same job: Nautilus Compass Memory MCP server.
How does MYCELIX compare with other MCP servers?
safety score 81/100 (higher than 62% of 48,255 servers); tools 23 (the typical server has 7); tools that change things 4% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to MYCELIX

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

  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B