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.

mdflow — Context OS for AI Coding Agents

OCI · GHCR.IO/YUBINBIN32-OPS/MDFLOW:0.3.7 · SCANNED SEP 20

Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.

+4 this week 31 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 & Transparency10
Schema Quality & AI Usability52
  • AI-judged instruction clarity (fair).Partial
  • Context-footprint check failed: tool/resource definitions use about 3341 tokens (~107/item across 31 items; 31 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
  • Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 31 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 32 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 mdflow — Context OS for AI Coding Agents MCP server?

mdflow — Context OS for AI Coding Agents runs locally as a container image, launched with docker run --rm -i ghcr.io/yubinbin32-ops/mdflow:0.3.7. 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/yubinbin32-ops/mdflow:0.3.7

# add to Claude Code
claude mcp add yubinbin32-ops-mdflow -- docker run --rm -i ghcr.io/yubinbin32-ops/mdflow:0.3.7
// .cursor/mcp.json
{
  "mcpServers": {
    "yubinbin32-ops-mdflow": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/mdflow:0.3.7"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "yubinbin32-ops-mdflow": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/mdflow:0.3.7"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add yubinbin32-ops-mdflow -- docker run --rm -i ghcr.io/yubinbin32-ops/mdflow:0.3.7
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "yubinbin32-ops-mdflow": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/mdflow:0.3.7"
      ],
      "enabled": true
    }
  }
}
# ~/.hermes/config.yaml
mcp_servers:
  yubinbin32-ops-mdflow:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/yubinbin32-ops/mdflow:0.3.7"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "yubinbin32-ops-mdflow": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/mdflow:0.3.7"
      ]
    }
  }
}
// mcp.json
{
  "mcpServers": {
    "yubinbin32-ops-mdflow": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/yubinbin32-ops/mdflow:0.3.7"
      ]
    }
  }
}
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.

  • 19 Sept 26 +4
    • Stability: unverified → 0.27 functional
  • 12 Sept 26 −5
    • Source repository: pass → fail security
  • 11 Sept 26 32

    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 20 Sept 2026 · Analysed oci/ghcr.io/yubinbin32-ops/mdflow:0.3.7

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 · 31 exposed · ~3,059 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
architecture_connect ~101

Connect two architecture Blocks with a validated Link in one simple call without crafting manual operations.

NameTypeReqDescription
actorstring
contractstring
includeStructuredboolean
kindstring
labelstring
projectRootstring
reasonstring
sourceIdstringyes
targetIdstringyes
taskContextIdstring

No output schema declared.

No examples provided.

architecture_link_suggest ~61

Suggest high-confidence architectural links for an architecture Block based on AST source imports and layered conventions.

NameTypeReqDescription
blockIdstringyes
includeStructuredboolean
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

block_seal ~111

Seal a verified Block implementation as complete. Requires valid current SourceBindings and a fresh passed direct Checkpoint; an executionId, when supplied, must be a successful receipt cited by that Checkpoint.

NameTypeReqDescription
actorstring
blockIdstringyes
checkpointIdstring
executionIdstring
includeStructuredboolean
projectRootstring
reasonstring
taskContextIdstring

No output schema declared.

No examples provided.

chain_code_stream ~98

Return locator-only source indexes along a Chain: path, symbol, signature, derived line range, source status, and contract. Never returns implementation bodies.

NameTypeReqDescription
chainIdstringyes
includeStructuredboolean
maxLinesPerSymbolinteger
maxTotalCharsinteger
modestring
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

change_set_revert ~124

Create a new reverse ChangeSet for a safe, fully reversible update-only ChangeSet. Original History is preserved; stale or unsupported changes are rejected instead of partially reverted.

NameTypeReqDescription
actorstring
chainScopeIdstring
changeSetIdstringyes
gitHeadstring|null
includeStructuredboolean
planIdstring
projectRootstring
reasonstring
taskstring
taskContextIdstring

No output schema declared.

No examples provided.

changes_since ~84

Read only graph/checkpoint mutations after a known change sequence. Use this for live synchronization and compact read-back instead of reloading the project.

NameTypeReqDescription
includeStructuredboolean
limitinteger
projectRootstring
sequenceinteger
sourceSyncRevisioninteger
taskContextIdstring

No output schema declared.

No examples provided.

checkpoint_list ~132

List checkpoints by status, target, Plan or ChainScope, including standalone checkpoints that are not referenced by any Plan. Use this for a compact verification inbox instead of opening every entity.

NameTypeReqDescription
chainScopeIdstring
includeStructuredboolean
limitinteger
localestring
planIdstring
projectRootstring
statusstring
targetIdstring
targetTypestring
taskContextIdstring
unassignedOnlyboolean

No output schema declared.

No examples provided.

checkpoint_record ~212

Create or update a checkpoint with evidence. Passed checkpoints are the only basis for healthy completion states.

NameTypeReqDescription
actorstring
aggregationPolicyobject
chainScopeIdstring
checkpointKindstring
coveragestring
criteriastring
eligibleAfterChildrenboolean
evidencearray
evidenceExecutionIdsarray
evidenceLevelstring
expectedRevisioninteger
gitHeadstring|null
idstring
includeStructuredboolean
invalidatedAtstring|null
planIdstring
projectRootstring
requiredEvidenceLevelstring
statusstringyes
targetIdstringyes
targetTypestringyes
taskContextIdstring
titlestringyes

No output schema declared.

No examples provided.

checkpoint_refresh_candidates ~70

List stale checkpoints that a recorded execution receipt can refresh. Does not auto-pass checkpoints; it only maps changed bindings onto retest_required items.

NameTypeReqDescription
executionIdstring
includeStructuredboolean
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

context_for_task ~95

Get a budgeted Markdown context pack for the current development task. Use at task start and expand only selected refs.

NameTypeReqDescription
budgetCharsinteger
focusRefsarray
includeStructuredboolean
localestring
maxCharsinteger
projectRootstring
taskstringyes
taskContextIdstring

No output schema declared.

No examples provided.

decision_list ~74

Read the compact project-scoped Decision index. Bodies, rationale, alternatives, and consequences are omitted; use decision_open or entity_open(type=decision) for one record.

NameTypeReqDescription
includeStructuredboolean
localestring
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

decision_open ~77

Open one architecture Decision. Returns its rationale, alternatives, consequences, scope, supersession, and compact History.

NameTypeReqDescription
historyLimitinteger
idstringyes
includeStructuredboolean
localestring
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

entity_open ~82

Open one Block, Chain, Link, Plan, or Decision with only relevant details and recent History.

NameTypeReqDescription
historyLimitinteger
idstringyes
includeStructuredboolean
localestring
projectRootstring
taskContextIdstring
typestringyes

No output schema declared.

No examples provided.

foundation_plan_create ~151

Generate one Foundation Plan from every non-deprecated unimplemented Block. Because this is an explicit implementation/verification Plan, the operation creates missing atomic Block checkpoints, direct Block PlanChanges, dependency-ordered parallel steps, Chain integration gates, and a final Plan acceptance gate in one transaction; plain architecture-only create_block does not.

NameTypeReqDescription
actorstring
gitHeadstring|null
goalstring
idstring
includeStructuredboolean
projectRootstring
reasonstring
requiredEvidenceLevelstring
taskContextIdstring
titlestring

No output schema declared.

No examples provided.

graph_flow ~93

Declare architectural flows and pipelines using natural arrow expressions like 'block:A -> block:B -> block:C' or 'A -[calls]-> B'. Automatically creates or updates links without complex JSON crafting.

NameTypeReqDescription
actorstring
flowstringyes
includeStructuredboolean
projectRootstring
reasonstring
taskContextIdstring

No output schema declared.

No examples provided.

graph_mutate ~209

Atomically create or patch Blocks, project-scoped Decisions, global Links, Chain paths, independent Plans, atomic Checkpoints, Background scopes, Decision scopes, and source refs. Decisions are not Canvas Blocks and never enter Block/Chain/Plan coverage. A plain create_block records architecture only; use create_checkpoint in the same ChangeSet when a requirement, Plan, Chain gate, or explicit verification request makes the check necessary. Link kinds are flows_to, calls, reads, writes, depends_on, implements, validates, constrains, and supersedes. Keep each call small and provide expectedRevision for updates.

NameTypeReqDescription
actorstring
chainScopeIdstring
gitHeadstring|null
includeStructuredboolean
operationsarrayyes
planIdstring
projectRootstring
reasonstringyes
taskstring
taskContextIdstring

No output schema declared.

No examples provided.

graph_patch ~130

Apply a compact mdflow/1 Markdown-like patch. The server expands it into the same atomic ChangeSet used by graph_mutate, preserves omitted fields, and can create an atomic Block checkpoint with checkpoint=auto.

NameTypeReqDescription
actorstring
chainScopeIdstring
gitHeadstring|null
includeStructuredboolean
patchstringyes
planIdstring
projectRootstring
reasonstring
taskstring
taskContextIdstring

No output schema declared.

No examples provided.

graph_search ~80

Search graph entities and source paths without loading the entire project.

NameTypeReqDescription
includeStructuredboolean
kindsarray
limitinteger
localestring
projectRootstring
querystringyes
statesarray
taskContextIdstring

No output schema declared.

No examples provided.

graph_status ~62

Inspect project architecture health, live drift detection, isolated blocks, ghost blocks with code, and pending verification gates.

NameTypeReqDescription
includeStructuredboolean
localestring
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

graph_validate ~54

Validate global graph references, Chain paths, Plan targets, Background scopes, contracts, and checkpoint-backed completion.

NameTypeReqDescription
includeStructuredboolean
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

log_sanitize ~94

Sanitize build, test, or terminal command outputs. Strips ANSI noise, collapses routine compiler stdout, and isolates actionable failure stack traces to protect context window from token flooding.

NameTypeReqDescription
exitCodeinteger
includeStructuredboolean
maxCharsinteger
projectRootstring
rawOutputstringyes
taskContextIdstring

No output schema declared.

No examples provided.

plan_context ~97

Read one Plan as a compact hierarchical development document: overview, ordered ChainScopes, inline Block/Link/Chain changes, checkpoint gates, and exact source refs. This is the primary read before implementing a Plan.

NameTypeReqDescription
idstringyes
includeStructuredboolean
localestring
maxCharsinteger
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

project_map ~68

Read a compact project map with architecture coverage, ordered Plans, Chain paths, explicit integration gates, and source-sync status without loading entity bodies.

NameTypeReqDescription
includeStructuredboolean
localestring
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

project_register ~67

Register an existing directory as an mdflow project. This creates only .mdflow/project.json and is idempotent when the descriptor already exists.

NameTypeReqDescription
idstring
includeStructuredboolean
namestring
projectRootstringyes

No output schema declared.

No examples provided.

run_command ~109

Run one project-local command and return only a redacted, compressed terminal summary. Raw stdout/stderr never enters the MCP response; use this gateway for tests, builds, and mutation verification.

NameTypeReqDescription
commandstringyes
cwdstring
executionKindstring
includeStructuredboolean
maxCharsinteger
projectRootstring
taskContextIdstring
timeoutMsinteger

No output schema declared.

No examples provided.

source_binding_accept ~90

Persist explicitly selected AST source binding candidates for a Block. Every candidate is re-resolved against current source before a SourceRef is created.

NameTypeReqDescription
actorstring
bindingsarrayyes
blockIdstringyes
includeStructuredboolean
projectRootstring
reasonstring
taskContextIdstring

No output schema declared.

No examples provided.

source_binding_suggest ~87

Suggest source bindings for a Block from AST symbols and project semantics. Suggestions are read-only; use source_binding_accept to persist an explicitly chosen candidate.

NameTypeReqDescription
blockIdstringyes
includeStructuredboolean
limitinteger
maxFilesinteger
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

source_sync ~79

Scan current files for bound symbols without loading source into the response. Reports moved, changed, missing, or ambiguous bindings and affected Blocks/Chains.

NameTypeReqDescription
includeStructuredboolean
includeUnchangedboolean
projectRootstring
sinceRevisioninteger
taskContextIdstring

No output schema declared.

No examples provided.

step_advance ~95

Advance the active step of a Plan to complete, automatically updating progress and pointing nowDoing to the next step.

NameTypeReqDescription
includeStructuredboolean
nextStepIdstring
planIdstring
projectRootstring
statusstring
stepIdstring
summarystring
taskContextIdstring

No output schema declared.

No examples provided.

timeline_sync ~105

Synchronize development cursor and active focus across conversations. Updates nowDoing, nextUp, and active step in the timeline.

NameTypeReqDescription
includeStructuredboolean
lastFinishedstring
nextUpstring
nowDoingstring
planIdstring
projectRootstring
stepIdstring
taskContextIdstring
touchedFilesarray

No output schema declared.

No examples provided.

timeline_view ~68

Read the unified project Timeline: execution phases, ordered plans (P0 > P1 > P2), and current active cursor (nowDoing, nextUp, lastFinished).

NameTypeReqDescription
includeStructuredboolean
projectRootstring
taskContextIdstring

No output schema declared.

No examples provided.

Common questions

What is the mdflow — Context OS for AI Coding Agents MCP server?

mdflow — Context OS for AI Coding Agents is an MCP server listed in the public MCP registry as io.github.yubinbin32-ops/mdflow. Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback. This page covers its container image (ghcr.io/yubinbin32-ops/mdflow:0.3.7).

Is the mdflow — Context OS for AI Coding Agents MCP server safe to use?

mdflow — Context OS for AI Coding Agents scores 31 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 mdflow — Context OS for AI Coding Agents MCP server expose?

mdflow — Context OS for AI Coding Agents exposes 31 tools: project_register, project_map, decision_list, decision_open, chain_code_stream, and 26 more. Their descriptions and schemas cost roughly 3,059 tokens of context every time the server is loaded.

Is the mdflow — Context OS for AI Coding Agents MCP server still maintained?

mdflow — Context OS for AI Coding Agents 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.