MCP.Market

Solfleet MCP server

by sanjeevkkansal·io.github.sanjeevkkansal/solfleet·v0.1.1

Agent-safe fleet management for independent Solana validators and RPC nodes

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

0 stars19 downloads/wk

Reviews

Write one

Nobody has reviewed Solfleet yet.

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

Solfleet tools (15)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • audit_log

    Recent audit entries (every dry-run and execute), newest first. Optionally filtered to one node.

  • bootstrap_builder_host

    Install the build toolchain + deps (Rust, protoc, libclang-dev, ...) on a builder host so it can compile agave from source. Dry-run by default; confirm=true runs it (idempotent) and records to the audit log. Run once per builder before the first upgrade/provision.

  • dns_pool_eject

    Manually pull a node from its DNS pool(s). Dry-run unless confirm=true. Refuses to empty a pool (last-member protection). Audited.

  • dns_pool_restore

    Manually add a node back to its DNS pool(s). Dry-run unless confirm=true. Audited.

  • dns_pool_status

    Current members of each managed DNS pool, mapped back to node names. Read-only.

  • fleet_status

    Health of every node in the fleet, grouped by cluster: reachability, getHealth, version, slot lag vs the cluster reference RPC, and delinquency/stake for voting validators.

  • leader_schedule

    Upcoming leader slots for a validator and whether it's safe to restart now (no leader slot within min_window_minutes). Read-only; helps plan restarts/upgrades without skipping your own slots.

  • node_detail

    Full probe result for a single node by name, including its cluster's reference data.

  • plan_node_upgrade

    Dry-run plan for upgrading one node in place to target_version, using artifacts from the cluster's dedicated builder. Read-only: produces the ordered steps and policy preflight, changes nothing.

  • provision

    Bring up a bare host into a serving node: preflight, user, system tuning, disks, software install (via the builder), systemd unit, key check, start + catch-up.

  • restart

    Restart a node and wait for catch-up. RPC nodes cycle via systemctl; voting validators use a leader-aware safe-exit so they don't skip slots.

  • upgrade

    Upgrade one node in place to target_version: build on the cluster's builder, distribute + checksum-verify the agave + geyser artifact set, swap atomically, cycle (leader-aware for validators), and verify.

  • validate

    Read-only readiness check of the whole fleet: per-node SSH/service/ binary/disk/RPC, per-builder cores/RAM/disk/toolchain, and DNS credential presence. Returns pass/warn/fail per check; ok is true only when nothing failed. Changes nothing.

  • version_drift

    Compare each node's solana-core version against its cluster's reference RPC version. Drift does not always mean outdated (the reference may itself lag a release), but it flags what to look at.

  • vote_status

    Voting health of a validator that a plain RPC check can't show: in the vote set, voting vs delinquent, epoch credits, last vote, root slot, commission, activated stake, identity SOL balance (+ low-balance warning; a validator pays vote fees every slot), catch-up, and the next leader window. Read-only.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan20 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 92 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Solfleet compares

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

Safety score
82/100
higher than 65% of 4,460 AI and agents servers
Tools
15
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
19
more than 5% of 1,538 AI and agents servers with a package

What its tools let an agent do: 14 read · 1 run or deploy

Install Solfleet in Claude Code, Cursor or VS Code

claude mcp add solfleet -- uvx solfleet
Add to Cursor

What the publisher says

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

solfleet

Agent-safe fleet management for independent Solana validators and RPC nodes. One config file describes your fleet across devnet, testnet, and mainnet. An MCP server (and a CLI) exposes Solana-aware status, safe in-place upgrades, and health-driven DNS failover to Claude or any MCP client. Every operation that changes a node is dry-run by default, policy-gated, and audited. solfleet never reads or moves your keypairs.

See PLAN.md for the roadmap and design notes.

Architecture

solfleet runs on the operator's machine (or a small VM). It talks to the fleet over JSON-RPC (read) and SSH/scp (act), builds artifacts on a separate build host, computes slot lag against each cluster's reference RPC, and manages failover records at the DNS provider. Every mutation flows through one gate and is written to a SQLite audit log.

flowchart TB
  claude["Claude / any MCP client"]

  subgraph operator["operator machine"]
    mcp["solfleet-mcp (stdio)"]
    cli["solfleet CLI"]
    core["core: probe · safety gate · executor · dns"]
    audit[("audit log (SQLite)")]
    claude -->|MCP| mcp
    mcp --> core
    cli --> core
    core --> audit
  end

  builder["build host (agave + geyser from source)"]
  ref["cluster reference RPC"]
  dns["DNS provider (Cloudflare / Route53)"]

  subgraph fleet["fleet: devnet / testnet / mainnet"]
    rpc["RPC nodes"]
    val["voting validators"]
  end

  core -->|JSON-RPC :8899| rpc
  core -->|JSON-RPC :8899| val
  core -->|SSH / scp| rpc
  core -->|SSH / scp| val
  core -->|SSH build, fetch artifacts| builder
  builder -. "artifact set + sha256" .-> core
  core -->|slot lag / delinquency| ref
  core -->|eject / restore A records| dns

How an in-place upgrade runs

sequenceDiagram
  actor Op as Claude / operator
  participant SF as solfleet
  participant B as build host
  participant N as node
  participant R as reference RPC
  Op->>SF: upgrade node to version (confirm)
  SF->>SF: gate, policy + preflight (else stop)
  SF->>B: build agave + geyser (or reuse cache)
  B-->>SF: artifact set + sha256
  SF->>N: scp artifacts as dest.solfleet-new
  SF->>N: sha256 on node matches builder (else abort)
  alt RPC node
    SF->>N: systemctl stop
    SF->>N: atomic swap (binary + geyser + marker)
    SF->>N: systemctl start
  else voting validator
    SF->>N: atomic swap (binary + geyser + marker)
    SF->>N: agave-validator exit (leader-aware), systemd relaunches
  end
  loop until healthy and caught up
    SF->>R: getSlot
    SF->>N: getHealth / getSlot
  end
  SF->>SF: verify reported version, write audit entry

How failover runs

sequenceDiagram
  participant SF as solfleet watch
  participant N as pool members
  participant R as reference RPC
  participant D as DNS provider
  loop every interval
    SF->>N: getHealth / getSlot
    SF->>R: getSlot (cluster head)
    SF->>SF: per member: unhealthy, lag over limit, or delinquent
    alt every member failing
      SF->>SF: keep current records (never empty the pool)
    else at least one healthy
      SF->>D: ensure TXT ownership marker
      SF->>D: remove A record of each failing member
      SF->>D: add A record of each recovered member
      SF->>SF: write audit entry
    end
  end

Why

Shortened. The full README is on GitHub.

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

Solfleet: common questions

Is Solfleet MCP server safe?
Mostly: it is graded B (82/100). Read the Solfleet safety report
How do I install Solfleet?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Solfleet need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Solfleet maintained?
The last commit was 131 days ago (2026-06-26). The latest release is v0.1.1.
What can I use instead of Solfleet?
Servers from other publishers that do the same job: 3D AI Agent Avatar MCP server.
How does Solfleet compare with other AI and agents MCP servers?
safety score 82/100 (higher than 65% of 4,460 AI and agents servers); tools 15 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Solfleet

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

  • 3D AI Agent Avatar
    3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.
    B