Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Atomadic Forge

REMOTE · FORGE.ATOMADIC.TECH · 2 COMPONENTS

Architecture compiler for AI code. 11 tools, 92 actions, 872 Lean4 proofs, 100/100 self-cert.

+33 this week 56 Trust /100

Last scanned (9 hours ago)

Scores higher than 43% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Developer Tools

Deprecated

This server is marked deprecated in the MCP registry. The registry records this reason: Retired: forge.atomadic.tech/mcp returns 404 and the PyPI package is a retired shim. Live server: io.github.atomadictech/aaaa-nexus. Public repo: github.com/atomadictech/atomadic-mcp.

Recent critical change

Authorization (1 Nov 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability49
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 3129 tokens (~46/item across 68 items; 68 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
  • Stability check failed: schema churn in the 4 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 13% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 68 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 69 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 5 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 9 to 13.

  • 4 Nov 26 0
    • Stability: 0.07 → fail ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “compliance_check” rewrote its description, which is the text the model reads security
    • “compliance_check” dropped the required parameter “data_type” ▼ functional
    • “compliance_check” dropped the required parameter “jurisdiction” ▼ functional
    • “compliance_check” dropped the required parameter “operation” ▼ functional
    • Schema quality: poor → fair functional
    • Server version: 124 → 126 functional
    • “compliance_check” added an optional parameter “chain_depth” cosmetic
    • “compliance_check” added an optional parameter “description” cosmetic
    • “compliance_check” added an optional parameter “kl_divergence” cosmetic
  • 3 Nov 26 +1
    • Server version: 0.6.9 → 124 functional
  • 2 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 1 Nov 26 +31
    • Authorization: unverified → fail ▼ critical
    • Injection markers: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • First check of Judged manipulation: pass security
    • MCP protocol: unverified → fail ▼ functional
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Schema quality: pass functional
    • First check of Destructive annotations: pass functional
    • First check of Schema quality: poor functional
    • First check of Schema quality: fail functional
    • First check of Tool coverage: 11 functional
  • 26 Oct 26 0
    • Transport: Transport check failed: declared streamable-http, but the endpoint returned HTTP 405. security
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://forge.atomadic.tech/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=forge.atomadic.tech CN=WE1,O=Google Trust Services,C=US 25 Oct 2026 23 Jan 2027 ECDSA 256 ECDSA-SHA256 320b49c41110ab580e9edccebadcda39
SANs: forge.atomadic.tech
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of forge.atomadic.tech. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
tech. present 2185 13 Verified
atomadic.tech. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://forge.atomadic.tech/mcp Verified 200
http (plaintext) http://forge.atomadic.tech/mcp HTTPS enforced 301 https://forge.atomadic.tech/mcp
MCP tools · 68 exposed · ~2,952 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
render_polyglot_roundtrip_pure ~98

[Fuse product · entitlement: fuse · FREE_R2_DEMO] Syntax-as-Data polyglot render head: source -> language-neutral logic IR -> source in target language. Canonical demo examples baked to R2 (4 examples × 12 languages). Live emit of novel inputs via the SDK.

NameTypeReqDescription
atom_namestringyes–
languagestring––
source_textstringyes–

No output schema declared.

No examples provided.

reputation_record ~47

[agents] Record agent interaction

NameTypeReqDescription
agent_idstringyes–
counterparty_idstring––
interaction_typestringyes–
outcomestringyes–

No output schema declared.

No examples provided.

rng_quantum ~19

[inference] Quantum random number with proof

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

rng_verify ~18

[inference] Verify current epoch random value

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

route_capability ~54

[Ledger product, entitlement: ledger] Route a natural-language intent to a deterministic capability/pipeline coordinate. 3 free calls/day, then entitlement 'ledger'.

NameTypeReqDescription
intentstringyesThe natural-language intent to route.

No output schema declared.

No examples provided.

security_zero_day ~31

[security] Zero-day threat assessment

NameTypeReqDescription
contextobject––
targetstringyes–

No output schema declared.

No examples provided.

sla_register ~38

[agents] Register an SLA

NameTypeReqDescription
consumer_idstringyes–
provider_idstringyes–
termsobjectyes–

No output schema declared.

No examples provided.

sla_report ~38

[agents] Report SLA violation

NameTypeReqDescription
descriptionstring––
sla_idstringyes–
violation_typestringyes–

No output schema declared.

No examples provided.

swarm_inbox ~16

[agents] Poll swarm inbox

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

swarm_relay ~44

[agents] Relay message through swarm

NameTypeReqDescription
messageobjectyes–
target_agent_idstringyes–
ttlinteger–Hop limit for relay

No output schema declared.

No examples provided.

text_keywords ~30

[inference] Keyword extraction

NameTypeReqDescription
max_keywordsinteger––
textstringyes–

No output schema declared.

No examples provided.

text_sentiment ~24

[inference] Sentiment analysis

NameTypeReqDescription
textstringyes–

No output schema declared.

No examples provided.

text_summarize ~25

[inference] Text summarization

NameTypeReqDescription
textstringyes–

No output schema declared.

No examples provided.

threat_score ~31

[security] Multi-vector threat score

NameTypeReqDescription
agent_idstringyes–
contextstring––

No output schema declared.

No examples provided.

trust_decay ~16

[trust] Current trust ceiling value

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

trust_history ~23

[trust] Trust score history

NameTypeReqDescription
agent_idstringyes–

No output schema declared.

No examples provided.

trust_score ~24

[trust] Bounded trust score

NameTypeReqDescription
agent_idstringyes–

No output schema declared.

No examples provided.

verify_settlement ~85

[Ledger product, entitlement: ledger] Proof-gated settlement: recompute the work digest and authorize a payout only if the claimed digest verifies GREEN. No proof, no payout. 3 free calls/day, then entitlement 'ledger'.

NameTypeReqDescription
claimed_digeststring–Claimed digest the payout is conditioned on.
inputsobjectyesThe work payload backing the settlement.

No output schema declared.

No examples provided.

Install

How do I install the Atomadic Forge MCP server?

Atomadic Forge is a hosted endpoint at https://forge.atomadic.tech/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · forge.atomadic.tech

# add to Claude Code
claude mcp add --transport http atomadictech-atomadic-forge 'https://forge.atomadic.tech/mcp'
Common questions

What is the Atomadic Forge MCP server?

Atomadic Forge is an MCP server listed in the public MCP registry as io.github.atomadictech/atomadic-forge. Architecture compiler for AI code. 11 tools, 92 actions, 872 Lean4 proofs, 100/100 self-cert. This page covers its hosted endpoint (https://forge.atomadic.tech/mcp).

Is the Atomadic Forge MCP server safe to use?

Atomadic Forge scores 56 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Atomadic Forge MCP server expose?

Atomadic Forge exposes 68 tools: murmuration, agents_contradiction, agents_intent_classify, agents_plan, agents_register, and 63 more. Their descriptions and schemas cost roughly 2,952 tokens of context every time the server is loaded.

Does the Atomadic Forge MCP server require authentication?

No. We connected to Atomadic Forge without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Atomadic Forge MCP server still maintained?

Atomadic Forge is marked deprecated in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.