pod
Other formats agents might prefer:
markdownjsonllms.txt

Agent? You probably want markdown or json, or Pod over MCP.

Reported issues for CLEO MCP Server

Pod holds 17 of 20 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to CLEO MCP Server.

Most discussed

[Feature] Add cleo doctor --full or cleo smoke for operational self-validation

Feature Request

Problem

CLEO has 215 MCP operations across 10 domains and 95+ CLI commands, but no way to validate that they actually work after installation or upgrade. The current `cleo doctor` only checks file/DB existence — it doesn't test operational correctness.

During the v2026.3.60 → v2026.3.65 verification cycle, bugs like the `phases` crash (#77), brain.db migration failure (#65), and 21 silent-empty commands (#70) all passed `doctor` with flying colors because doctor o

Read the thread · 2026-03-23 · closed · 3 comments

BUG: cleo exists routes to unregistered query:tasks.exists operation

Bug Description

cleo exists <taskId> fails with:

Unknown operation: query:tasks.exists (exit code 2)

The CLI command exists and accepts a task ID argument, but routes to query:tasks.exists which is not registered in the MCP operation matrix.

Steps to Reproduce

cleo exists T001
# Error: Unknown operation: query:tasks.exists (exit code 2)

cleo exists T999
# Error: Unknown operation: query:tasks.exists (exit code 2)

Expected Behavior

  • cleo exists T001 → e

Read the thread · 2026-03-23 · closed · 3 comments

[Bug]:Legacy cleo-mcp-reaper kills active Codex CLI sessions and needs upgrade-time migration

Bug Report

Impact

Active Codex CLI sessions are deterministically terminated after their npm Node launcher is older than 900 seconds. This can discard in-progress terminal work and was initially misidentified as a Codex crash.

Reproduction and evidence

A host-local user timer ran every 10 minutes and invoked ~/.local/bin/cleo-mcp-reaper.sh. The helper selected every process where /proc/PID/comm equals MainThread, age is at least 900 seconds, and the ancestry lacks a live `cla

Read the thread · 2026-08-11 · open · 2 comments

[Bug]:implemented gate commit-reachability rejects development-merged work (only checks task/ or main)

Bug Report

Summary

The implemented gate's commit atom only accepts commits reachable from task/<taskId> or main. Work merged to an integration branch (development) via a SHARED task branch (one PR covering multiple task IDs) cannot be reconciled — only the lead task's branch exists.

Repro

PR #6 (task/T028) covered T028–T031. After merge to development:

$ git log --all --grep T030   # 763e161 refactor(T030)... exists on development
$ cleo verify T030 --gate implemented

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/1116) · 2026-06-30 · closed · 2 comments

### BUG: cleo phases / phase list crashes with TypeError: Cannot read properties of undefined (reading 'length')

## Bug Description

`cleo phases` and `cleo phase list` both crash with an unhandled TypeError:

TypeError: Cannot read properties of undefined (reading 'length') at paginate (dist/cli/index.js:15414:23) at PipelineHandler.queryPhase (dist/cli/index.js:90708:22)


Exit code: 1. Reproducible via both CLI and MCP (`pipeline.phase.list`).

## Steps to Reproduce

```bash
cleo phases
# TypeError: Cannot read properties of undefined (reading 'length')

cleo phase list
# Same crash

Read the thread · 2026-03-23 · closed · 2 comments

[Bug]: lifecycle.sh line 529: EXIT_USAGE unbound variable blocks all lifecycle progression

What happened?

Description

The lifecycle.progress operation fails with an unbound variable error, blocking ALL lifecycle stage progression for epics.

Reproduction

cleo_mutate domain=lifecycle operation=progress params={epicId: T016, stage: research, status: done}

Expected

Lifecycle stage recorded successfully.

Actual

{
  "success": false,
  "error": {
    "code": "E_UNKNOWN",
    "exitCode": 1,
    "message": "/home/keatonhoskins/.cleo/scripts/lifecycle.sh: 

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/20) · 2026-02-13 · closed · 2 comments

### [Bug]:Evidence tool: pr: atom hardcodes cleocode's own required workflows, rejecting every PR in a consumer repo

### Bug Report

## What happens

`cleo verify T### --gate testsPassed --evidence "pr:96"` fails in the PepsVida repo with:

E_EVIDENCE_TESTS_FAILED Required workflows did not run for this PR: Lockfile Check, Contracts Dep Lint. Cannot accept pr atom — required gates were skipped.


`Lockfile Check` and `Contracts Dep Lint` are workflows that exist in the **cleocode** repo. They do not exist in PepsVida and never have. The check appears to compare against a hardcoded list rather than again

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/1192) · 2026-08-19 · closed · 1 comment

### [Bug] cleo find with empty string errors instead of returning all tasks

### Bug Report

Running `cleo find ""` returns an error requiring a search query, but agents often need to list all tasks for discovery.

**Steps to reproduce:**
1. Run `cleo find ""`
2. Expect: all tasks returned (or a helpful suggestion)
3. Actual: `E_INVALID_INPUT: Search query or --id is required`

**Expected behavior:** Either:
- Empty string search returns all tasks (like `cleo find` with a wildcard)
- Or the error message suggests `cleo find '*'` or another way to list all tasks

**Contex

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/85) · 2026-03-26 · closed · 1 comment

## Most recent

### [Bug]:Evidence cache lock acquisition fails under concurrent agent sessions; verify calls hang for minutes

### Bug Report

## Summary
With multiple agent sessions active against the same project (the normal multi-agent setup), `cleo verify` intermittently fails with:

`Failed to acquire lock: /mnt/projects/PepsVida/.cleo/cache/evidence/<hash>.json`

and, more often, verify/complete calls hang for 2-5 minutes (local ollama enrichment + lock contention) and time out scripted gate closeouts.

## Repro (cleo v2026.7.2, node v24.16.0, linux, 3 concurrent agent sessions)

while other sessions run cleo

Read the thread · 2026-08-01 · closed · 0 comments

[Bug] Memory brain DB migration failure: T528 duplicate column blocks cleo memory observe across sessions

Bug Report

Observed behavior

During the LLMtxt Storage Evolution delivery (2026-04-17), cleo memory observe "..." --title "..." fails consistently across at least 10 different background subagent sessions with a schema/DB migration error described by the agents as "pre-existing brain DB migration issue, T528 duplicate column".

Representative return messages from subagents:

"Memory observe failed due to a CLEO brain DB migration error (unrelated to T### work)" "The memory observe

Read the thread · 2026-04-17 · closed · 0 comments

BUG: All cleo issue subcommands fail — routes to unregistered MCP operations

Bug Description

All three cleo issue subcommands (bug, feature, help) fail with:

Unknown operation: mutate:tools.issue.add.<type>

Exit code: 2

The CLI commands route to MCP operations that are not registered in the operation matrix.

Steps to Reproduce

cleo issue bug --title "test" --body "test" --severity Blocker --area cli
# Error: Unknown operation: mutate:tools.issue.add.bug (exit code 2)

cleo issue feature --title "test" --body "test" --dryRun
# Error

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/64) · 2026-03-23 · closed · 1 comment

### BUG: cleo add/mutate tasks.add fails — missing pipeline_stage column not added by cleo upgrade

## Bug Description

Both `cleo add` (CLI) and `mutate tasks.add` (MCP) fail with:

no such column: "pipeline_stage" - should this be a string literal in single-quotes?


**Exit code:** 3 (`E_NOT_INITIALIZED`)  
**CLEO version:** 2026.3.60 (`@cleocode/cleo`)  
**Severity:** Blocker — cannot create any new tasks

The `tasks` table in `tasks.db` does not have a `pipeline_stage` column, but v2026.3.60 expects it in the INSERT statement. Running `cleo upgrade` does **not** fix the issue.

## S

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/63) · 2026-03-23 · closed · 1 comment

### Bug: require('crypto') in ESM module causes 'require is not defined' in native mode mutate operations

## Bug Description

All mutate operations (`tasks.create`, `tasks.update`, `tasks.complete`, `tasks.delete`, `tasks.archive`) fail with **"require is not defined"** when running in **native TypeScript mode** (without CLI installed).

Query operations work fine.

## Environment

- `@cleocode/mcp-server` v0.98.4
- Node.js v24.13.1
- Windows 11 / OpenCode + Claude Code
- Native mode (no `cleo` CLI installed globally)

## Root Cause

The package declares `"type": "module"` in `package.json` (ESM), b

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/45) · 2026-02-21 · closed · external user · 1 comment

### [Bug]: Gateway header comments show stale operation counts

### What happened?

The JSDoc header comments in query.ts and mutate.ts show outdated operation counts after the providers domain was added:

- query.ts line 8: says 'Total operations: 63' but actual EXPECTED_QUERY_COUNT is 66 (providers added 3 query ops: list, detect, inject_status)
- mutate.ts line 8: says 'Total operations: 60' but actual EXPECTED_MUTATE_COUNT is 61 (providers added 1 mutate op: inject)

The runtime EXPECTED_*_COUNT constants are correct (66/61) and match the actual counts, 

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/35) · 2026-02-14 · closed · 1 comment

### [Bug]: MCP issues handler ignores dryRun parameter

### What happened?

The issues domain handler in mcp-server/src/domains/issues.ts does not pass --dry-run to the CLI when params.dryRun is true. This causes real GitHub issues to be created even when dryRun: true is passed. The IssueCreateParams interface also lacks the dryRun field. Found during v0.94.0 regression testing — test issues #22, #23, #24 were created unintentionally.

**Severity**: Major
**Area**: mcp

### Are you using an AI agent?

Yes - AI agent filed this issue

---

## Environm

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/25) · 2026-02-13 · closed · 0 comments

### [Question]: MCP regression test help

### What do you need help with?

Testing create_help via MCP

### Are you using an AI agent?

Yes - AI agent filed this question

---

## Environment
| Component | Version |
|-----------|----------|
| CLEO | 0.94.1 |
| Bash | 5.3.0(1)-release |
| jq | jq-1.8.1 |
| OS | Linux 6.18.8-200.fc43.x86_64 x86_64 |
| Shell | bash |
| gh CLI | gh version 2.86.0 (2026-01-21) |
| Install | /home/keatonhoskins/.local/bin/cleo |

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/24) · 2026-02-13 · closed · 1 comment

### [Feature]: MCP regression test feature

### Problem or use case

Testing create_feature via MCP

### Are you using an AI agent?

Yes - AI agent filed this request

---

## Environment
| Component | Version |
|-----------|----------|
| CLEO | 0.94.1 |
| Bash | 5.3.0(1)-release |
| jq | jq-1.8.1 |
| OS | Linux 6.18.8-200.fc43.x86_64 x86_64 |
| Shell | bash |
| gh CLI | gh version 2.86.0 (2026-01-21) |
| Install | /home/keatonhoskins/.local/bin/cleo |

[Read the thread](https://github.com/kryptobaseddev/cleo/issues/23) · 2026-02-13 · closed · 1 comment

The remaining reports are on [the project's issue tracker](https://github.com/kryptobaseddev/cleo.git/issues).