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.

Conflux CRDT Shared State

PYPI · CONFLUX-STATE

Zero-dependency CRDT shared state and conflict-resolution MCP server for parallel AI agents.

Available components

−15 this week 66 Trust /100

Last scanned (15 hours ago)

Scores higher than 58% of PyPI servers

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to lolllll212/Conflux). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 7 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1128 tokens (~70/item across 16 items; 14 tools + 2 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "conflux_set_remove" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (14)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (2)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

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.

  • 17 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 14 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 13 Nov 26 66

    First indexed and scored.

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 21 Nov 2026 · Analysed pypi/conflux-state@0.9.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo lolllll212/Conflux
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/lolllll212/Conflux/.github/workflows/publish.yml@refs/heads/master
Rekor log index 3856356341
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:dbeda221cb154262e68871e0e0cdfbcd6c3a86fd91d28bd6b0c728005a8af8ad

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~1,081 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
conflux_batch ~59

Execute multiple CRDT mutations sequentially in one tool call (ops: register_set, mv_write, counter_add, set_add, set_remove).

NameTypeReqDescription
operationsarrayyesList of mutation specs: {op, key, value/delta/tag}.

No output schema declared.

No examples provided.

conflux_claim_resource ~125

Advisory file/task claim with TTL lease so parallel coding agents (Claude Code, Cursor) avoid editing the same file simultaneously. Reports 'conflict' if another agent holds an active lease.

NameTypeReqDescription
forceboolean–Steal the claim even if another agent's lease has not expired yet.
intentstring–Short note describing what this agent is doing with the resource.
resourcestringyesFile path or resource identifier (e.g. 'src/auth.py').
ttl_secondsnumber–Lease duration in seconds before automatic expiry (default 120).

No output schema declared.

No examples provided.

conflux_conflicts ~54

List all unresolved concurrent write conflicts across MVRegister keys, showing every competing agent's candidate value, causal dot ('tick:agent'), and current canonical winner.

NameTypeReqDescription
prefixstring–Optional key prefix to filter conflicts.

No output schema declared.

No examples provided.

conflux_counter_add ~66

Atomically increment (delta > 0) or decrement (delta < 0) a lock-free shared PNCounter across concurrent agents.

NameTypeReqDescription
deltainteger–Non-zero integer to add (positive increments, negative decrements).
keystringyesCounter key.

No output schema declared.

No examples provided.

conflux_mv_write ~118

Write a JSON value to a conflict-preserving Multi-Value Register (MVRegister). Sequential writes cleanly replace prior values, while un-synced concurrent writes from parallel agents are BOTH preserved in conflux_conflicts until resolved!

NameTypeReqDescription
keystringyesMVRegister key (e.g. 'spec.api_schema').
supersedesarray–Optional list of 'tick:agent' dots to supersede (defaults to all currently observed dots on this replica).
value–yesJSON-serializable value proposed by this agent.

No output schema declared.

No examples provided.

conflux_read ~69

Read the current converged value of a shared CRDT key (PNCounter int, LWWRegister JSON value, MVRegister winning value + active conflicts, or ORSet list).

NameTypeReqDescription
keystringyesShared state key (e.g. 'fleet.jobs_done' or 'arch.decision').

No output schema declared.

No examples provided.

conflux_register_set ~73

Write any JSON value to a Last-Writer-Wins (LWW) register in shared Conflux state. Concurrent writes resolve deterministically with zero locks.

NameTypeReqDescription
keystringyesRegister key to set.
value–yesAny JSON-serializable value (string, number, boolean, object, array).

No output schema declared.

No examples provided.

conflux_release_resource ~34

Release an advisory resource/file lease previously claimed by this agent.

NameTypeReqDescription
resourcestringyesFile path or resource identifier.

No output schema declared.

No examples provided.

conflux_resolve_conflict ~74

Causally resolve all currently observed concurrent MVRegister candidates on 'key' into a single merged/agreed JSON value, clearing the conflict across the mesh.

NameTypeReqDescription
keystringyesConflicted MVRegister key to resolve.
resolved_value–yesMerged/agreed JSON value superseding all prior candidates.

No output schema declared.

No examples provided.

conflux_set_add ~82

Add an item to a conflict-free Observed-Remove Set (ORSet) in shared state.

NameTypeReqDescription
keystringyesSet key (e.g. 'swarm.findings').
tagstring–Optional unique tag (save this tag if you plan to remove the item later).
value–yesJSON-serializable element to add.

No output schema declared.

No examples provided.

conflux_set_remove ~52

Tombstone-remove an element tag from a shared Observed-Remove Set (ORSet).

NameTypeReqDescription
keystringyesSet key.
tagstringyesTag previously used in conflux_set_add.

No output schema declared.

No examples provided.

conflux_snapshot ~68

Return a full JSON snapshot of all shared CRDT keys (optionally filtered by prefix), active MVRegister conflict count, and the canonical 64-hex SHA-256 state_hash.

NameTypeReqDescription
prefixstring–Optional key prefix filter (e.g. 'crew.' or 'tasks/').

No output schema declared.

No examples provided.

conflux_task_update ~122

Create or update a replicated multi-agent task record under 'tasks/<task_id>' (status: created | running | done | failed) so parallel agents coordinate work queues.

NameTypeReqDescription
errorstring–Optional error message when status='failed'.
kindstring–Task category/type (used when creating a task).
result––Optional JSON result payload when status='done'.
statusstringyesNew lifecycle status for the task.
stepstring–Optional current step label.
task_idstringyesUnique task identifier.

No output schema declared.

No examples provided.

conflux_watch_wait ~85

Wait up to timeout_seconds until 'key' changes from 'since_value' (or becomes non-null), enabling event-driven handoffs between parallel MCP agents.

NameTypeReqDescription
keystringyesKey to watch.
since_value––Return immediately once current value differs from since_value.
timeout_secondsnumber–Max seconds to wait (capped at 30s).

No output schema declared.

No examples provided.

Install

How do I install the Conflux CRDT Shared State MCP server?

Conflux CRDT Shared State runs locally as a PyPI package, launched with uvx conflux-state. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · conflux-state

# add to Claude Code
claude mcp add lolllll212-conflux-state -- uvx conflux-state
Common questions

What is the Conflux CRDT Shared State MCP server?

Conflux CRDT Shared State is an MCP server listed in the public MCP registry as io.github.lolllll212/conflux-state. Zero-dependency CRDT shared state and conflict-resolution MCP server for parallel AI agents. This page covers its PyPI package (conflux-state).

Is the Conflux CRDT Shared State MCP server safe to use?

Conflux CRDT Shared State scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 Conflux CRDT Shared State MCP server expose?

Conflux CRDT Shared State exposes 14 tools: conflux_read, conflux_snapshot, conflux_register_set, conflux_mv_write, conflux_conflicts, and 9 more. Their descriptions and schemas cost roughly 1,081 tokens of context every time the server is loaded.

Is the Conflux CRDT Shared State MCP server still maintained?

Conflux CRDT Shared State is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Conflux CRDT Shared State MCP server under?

Conflux CRDT Shared State declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Conflux CRDT Shared State MCP server?

VerifyMCP ran 14 checks on Conflux CRDT Shared State, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about Conflux CRDT Shared State: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.