MCP.Market

Forkmind MCP server

by Medhovarsh·io.github.Medhovarsh/forkmind·v0.9.0·3 stars

Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.

A88/100grade A
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

3 stars45 downloads/wk

Reviews

Write one

Nobody has reviewed Forkmind yet.

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

Forkmind tools (15)

write = sends, deletes, buys or posts

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

  • forkmind_children

    List the alternative continuations (branches) that fork from a node.

  • forkmind_context_digest

    Cheap probe: full digest and DAG structure for one capsule, no

  • forkmind_context_export

    Export a capsule as a passphrase-encrypted, self-contained bundle

  • forkmind_context_forget

    IRREVERSIBLY destroy a capsule: its encryption key is shredded and the

  • forkmind_context_import

    Import a bundle produced by forkmind_context_export. Every segment

  • forkmind_context_list

    Compact list of saved capsules (title, digest, size, age). Optional

  • forkmind_context_replicas

    Status of redundant capsule storage: each replica target with

  • forkmind_context_restore

    Decrypt and return capsule content (integrity-verified first). Pass

  • forkmind_context_save

    Offload conversation context into an immutable, encrypted DAG on disk.

  • forkmind_context_stats

    Aggregate stats across all capsules: count, bytes, estimated tokens

  • forkmind_get_node

    Fetch one node by id with full request + response payloads.

  • forkmind_lineage

    Return the full conversation path from the root to the given node —

  • forkmind_recent

    List the most recent captured LLM turns (newest first), compact.

  • forkmind_search

    Case-insensitive substring search across all captured requests/responses.

  • forkmind_stats

    Summary of the conversation tree: totals, roots, leaves, providers.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

no findings
  • Code scan26 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 37 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Forkmind compares

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

Safety score
88/100
higher than 85% of 1,761 Finance servers
Tools
15
the typical Finance server has 8
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
3
more than 83% of 946 Finance servers
Downloads a week
45
more than 42% of 421 Finance servers with a package

What its tools let an agent do: 15 create

Install Forkmind in Claude Code, Cursor or VS Code

Runs npx -y forkmind on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add forkmind -- npx -y forkmind
Add to Cursor

What the publisher says

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

ForkMind 🧠

Local-first LLM branching, debugging & context offloading

Treat your AI conversation history like a Git repository — capture every call, branch from any turn, and diff outcomes side by side. All on your machine.

Try in 10s · Features · Install · Quick start · MCP · Capsules

What you're seeing: the conversation DAG with a fork off the debug turn,

the node inspector (request/response, tokens, provenance), and the ⇄ Compare

view diffing two branches with per-token deltas. The green ● streaming

badge shows live capture — nodes appear as they're recorded.

ForkMind captures every LLM call into a local .forkmind/ directory, visualizes the conversation as a Directed Acyclic Graph (DAG), and lets you branch, diff, and replay from any point in the history. Works with any OpenAI-compatible API, defaulting to free, open-source models via Ollama — also Anthropic, Groq, OpenRouter, Together, vLLM, and LM Studio.

Static screenshot

Why

Debugging agentic / tool-calling flows means re-running the same prompt with tiny tweaks over and over, then scrolling through terminal logs to see what changed. ForkMind records each run as a node in a conversation tree, so instead of re-reading logs you see the whole history, branch from any turn, and compare outcomes visually.

Everything is plain JSON on disk. No database, no account, no telemetry — nothing leaves your machine except the LLM call you were already making.

Features

Shortened. The full README is on GitHub.

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

Forkmind: common questions

Is Forkmind MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Forkmind safety report
How do I install Forkmind?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Forkmind need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Forkmind maintained?
The last commit was 77 days ago (2026-08-19). The latest release is v0.9.0.
What can I use instead of Forkmind?
Servers from other publishers that do the same job: Blockrun MCP server, Yolfi Payments MCP server and AlgoVault — Crypto Quant Trade Calls MCP server.
How does Forkmind compare with other Finance MCP servers?
safety score 88/100 (higher than 85% of 1,761 Finance servers); tools 15 (the typical Finance server has 8); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Forkmind

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

  • Blockrun
    Web search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.
    B
  • Yolfi Payments MCP
    Let AI agents add Yolfi crypto checkout, paylinks, webhooks, and status checks.
    A
  • AlgoVault — Crypto Quant Trade Calls
    The Brain Layer for AI Trading Agents — quant calls + cross-venue arb across perp venues via MCP.
    A
  • Hive Intelligence MCP
    Evidence-backed crypto due diligence with sources, freshness, and a runtime receipt on every call.
    C
  • Pyth Pro MCP Server
    Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.
    A