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.

io.github.DojoGenesis/mcp

OCI · GHCR.IO/DOJOGENESIS/MCP:3.2.1 · SCANNED SEP 20

Practice library for coding agents: skill search/invoke, seed patches, scout, reflect, ADR writer

0 this week 53 Trust /100
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 Security0
  • Malware scan not yet available for this package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency45
Schema Quality & AI Usability84
  • 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 2352 tokens (~42/item across 56 items; 28 tools + 28 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "dojo_agent_chat" implies "send" 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 29 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.

Install

How do I install the io.github.DojoGenesis/mcp server?

io.github.DojoGenesis/mcp runs locally as a container image, launched with docker run --rm -i ghcr.io/dojogenesis/mcp:3.2.1. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/dojogenesis/mcp:3.2.1

# add to Claude Code
claude mcp add dojogenesis-mcp -- docker run --rm -i ghcr.io/dojogenesis/mcp:3.2.1
// .cursor/mcp.json
{
  "mcpServers": {
    "dojogenesis-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/dojogenesis/mcp:3.2.1"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dojogenesis-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/dojogenesis/mcp:3.2.1"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add dojogenesis-mcp -- docker run --rm -i ghcr.io/dojogenesis/mcp:3.2.1
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dojogenesis-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/dojogenesis/mcp:3.2.1"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  dojogenesis-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/dojogenesis/mcp:3.2.1"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dojogenesis-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/dojogenesis/mcp:3.2.1"
      ]
    }
  }
}
// mcp.json
{
  "mcpServers": {
    "dojogenesis-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/dojogenesis/mcp:3.2.1"
      ]
    }
  }
}
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.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 17 Sept 26 +1
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 10 Sept 26 +1
    • Stability: 0.97 → pass security
  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

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 20 Sept 2026 · Analysed oci/ghcr.io/dojogenesis/mcp:3.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 28 exposed · ~1,716 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
dojo_agent_chat ~48

Send a follow-up message to an existing agent by ID.

NameTypeReqDescription
agent_idstringyesThe agent ID to send the message to
messagestringyesThe message to send

No output schema declared.

No examples provided.

dojo_agent_dispatch ~93

Create and dispatch a new agent with an initial task message. Returns the agent ID and response.

NameTypeReqDescription
messagestringyesInitial task message for the agent
modestringAgent mode (e.g., 'focused', 'balanced', 'exploratory')
namestringyesAgent name
workspace_rootstringOptional workspace root path for the agent (defaults to server config)

No output schema declared.

No examples provided.

dojo_agent_list ~26

List all agents registered with the Gateway, including their mode, status, and disposition.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dojo_apply_seed ~71

Apply a Dojo seed patch (reusable thinking pattern) to a specific situation. Returns the seed's core insight formatted as active guidance with a checklist.

NameTypeReqDescription
seed_namestringyesThe name of the seed patch to apply
situationstringyesThe situation to apply the seed patch to

No output schema declared.

No examples provided.

dojo_converge ~37

Run a convergence check: git dirty files, recent commits, memory/seed counts. Returns RED/YELLOW/GREEN signal with guidance.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dojo_dispatch ~77

Dispatch a prompt to an LLM through the Dojo Gateway and return the reply. DISPATCH-CLASS: spends provider budget; on the public endpoint it requires a dispatch-enabled API key and is rate limited per key.

NameTypeReqDescription
promptstringyesThe prompt to send
session_idstringOptional gateway session id for continuity

No output schema declared.

No examples provided.

dojo_disposition_list ~27

List available ADA disposition presets with their pacing, depth, tone, and initiative axes.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dojo_disposition_set ~89

Set the active agent disposition. Writes the value to the top-level `defaults.disposition` key in ~/.dojo/settings.json (creates the file if missing). Local-only, no Gateway needed.

NameTypeReqDescription
dispositionstringyesThe disposition name to activate (e.g., 'focused', 'balanced', 'exploratory', 'deliberate'). Use dojo_disposition_list to see available options.

No output schema declared.

No examples provided.

dojo_fetch ~152

One tool to search AND fetch across the whole dojo store: Memory Hub, skills corpus, ADRs, and seed patches. Query mode returns a ranked, typed result list with fetchable ids; id mode (e.g. 'memory:night-shift-family', 'skill:debugging', 'adr:2026-07-05_x.md', 'seed:name') returns the full content.

NameTypeReqDescription
idstringTyped id 'store:key' to fetch full content
limitintegerMax merged results (default 8, max 25)
querystringSearch text (required unless id is given)
storesarrayStores to search (default: all)

No output schema declared.

No examples provided.

dojo_get_memory ~45

Fetch the full body of one Memory Hub entry by slug (as returned by dojo_search_memory / dojo_recent_memories).

NameTypeReqDescription
slugstringyesThe memory slug to fetch

No output schema declared.

No examples provided.

dojo_health ~20

Check Gateway health: status, version, providers, uptime.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dojo_invoke_skill ~74

Load a specific methodology skill by name. Returns the full workflow as actionable steps. Use dojo.search_skills or dojo.list_skills to find skill names.

NameTypeReqDescription
namestringyesThe exact name of the skill to invoke (e.g., 'strategic-scout', 'debugging', 'retrospective')

No output schema declared.

No examples provided.

dojo_list_skills ~109

List available methodology skills grouped by plugin category. Supports optional filtering by plugin name and pagination via limit/offset. Shows skill names and descriptions for use with dojo.invoke_skill.

NameTypeReqDescription
limitintegerMaximum number of skills to return (default 50).
offsetintegerNumber of skills to skip before returning results (default 0).
pluginstringOptional plugin name to filter results (e.g., 'strategic-thinking'). If omitted, all plugins are listed.

No output schema declared.

No examples provided.

dojo_log_decision ~114

Write an Architecture Decision Record (ADR) to disk. The only write-capable tool. Creates a persistent markdown artifact capturing a key decision with context, rationale, and consequences.

NameTypeReqDescription
consequencesstringyesWhat changes as a result. Both positive and negative.
contextstringyesWhy this decision is needed. What forces are at play?
decisionstringyesWhat was decided and why
titlestringyesShort title for the decision (e.g., 'Use PostgreSQL for persistence')

No output schema declared.

No examples provided.

dojo_memory_list ~28

List all memory entries from the Gateway. Returns ID, type, and content for each memory.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dojo_memory_search ~34

Search memory entries by query. Returns matching memories ranked by relevance.

NameTypeReqDescription
querystringyesSearch query for memory content

No output schema declared.

No examples provided.

dojo_memory_store ~60

Store a new memory entry in the Gateway. Accepts content text and optional type.

NameTypeReqDescription
contentstringyesThe memory content to store
typestringOptional memory type (e.g., 'feedback', 'project', 'user')

No output schema declared.

No examples provided.

dojo_project_decision ~33

Record a decision in the active project. Local-only.

NameTypeReqDescription
textstringyesThe decision text to record

No output schema declared.

No examples provided.

dojo_project_status ~31

Get the current project status: name, phase, tracks, and decisions. Local-only, no Gateway needed.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dojo_project_track ~61

Add or update a project track. Local-only.

NameTypeReqDescription
actionstringyesAction: 'add' or 'set'
namestringyesTrack name
statusstringTrack status (pending, in_progress, done, blocked)

No output schema declared.

No examples provided.

dojo_recent_memories ~69

List the most recently updated Memory Hub entries — orientation on connect. Optional type filter.

NameTypeReqDescription
limitintegerMax results (default 10, max 50)
typestringOptional type filter (e.g., 'project', 'feedback', 'reference', 'seed')

No output schema declared.

No examples provided.

dojo_reflect ~53

Structured reflection grounded in your methodology library. Searches skills and seeds matching your session description and returns relevant frameworks, patterns, and reflection questions.

NameTypeReqDescription
session_descriptionstringyesDescription of the current session or work being done

No output schema declared.

No examples provided.

dojo_scout ~59

Strategic analysis scaffold. Returns a 4-step framework for navigating strategic decisions: identify tension, scout routes, synthesize, and decide. Claude fills in the judgment.

NameTypeReqDescription
situationstringyesThe strategic situation, decision, or tension to analyze

No output schema declared.

No examples provided.

dojo_search_memory ~129

Search the shared Memory Hub: ranked full-text search over the TresPies/DojoGenesis institutional memory (400+ entries mirrored from the orchestration repo — projects, feedback, references, seeds). Supports websearch syntax (quoted phrases, OR, -exclusions). Distinct from dojo_memory_search, which queries gateway session memory.

NameTypeReqDescription
limitintegerMax results (default 8, max 25)
querystringyesWhat to search for
typestringOptional type filter (e.g., 'project', 'feedback', 'reference', 'seed')

No output schema declared.

No examples provided.

dojo_search_skills ~58

Search the methodology library for skills matching a query. Returns top matches with descriptions and usage guidance.

NameTypeReqDescription
querystringyesWhat you're looking for (e.g., 'how to debug', 'write a spec', 'run a retro')

No output schema declared.

No examples provided.

dojo_seed_create ~66

Plant a new seed in the Gateway garden. Requires a name and content.

NameTypeReqDescription
contentstringyesThe seed content — the reusable pattern or insight
descriptionstringOptional one-line description
namestringyesSeed name (short, hyphenated)

No output schema declared.

No examples provided.

dojo_seed_list ~24

List all seeds from the Gateway garden, or hardcoded seeds if offline.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dojo_seed_search ~29

Search seeds by keyword in name and content.

NameTypeReqDescription
querystringyesSearch query for seeds

No output schema declared.

No examples provided.

Common questions

What is the io.github.DojoGenesis/mcp server?

io.github.DojoGenesis/mcp is listed in the public MCP registry as io.github.DojoGenesis/mcp. Practice library for coding agents: skill search/invoke, seed patches, scout, reflect, ADR writer. This page covers its container image (ghcr.io/dojogenesis/mcp:3.2.1).

Is the io.github.DojoGenesis/mcp server safe to use?

io.github.DojoGenesis/mcp scores 53 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 io.github.DojoGenesis/mcp server expose?

io.github.DojoGenesis/mcp exposes 28 tools: dojo_agent_chat, dojo_agent_dispatch, dojo_agent_list, dojo_apply_seed, dojo_converge, and 23 more. Their descriptions and schemas cost roughly 1,716 tokens of context every time the server is loaded.

Is the io.github.DojoGenesis/mcp server still maintained?

io.github.DojoGenesis/mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 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 io.github.DojoGenesis/mcp server under?

io.github.DojoGenesis/mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.