Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/henningziech/claude-error-collector-mcp.git
cd claude-error-collector-mcp
npm install
npm run buildRegister it in Claude Code
claude mcp add claude-error-collector -- node /path/to/claude-error-collector-mcp/dist/index.jsReplace any placeholder paths in the command with the real path on your machine.
Make your agent remember this setup
claude-error-collector's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Automatically records user corrections as persistent rules in CLAUDE.md
- Supports both project-specific and global rule storage
- Includes metadata like date and category for rule organization
- Provides duplicate detection to prevent redundant rule entries
- Allows for listing, updating, and deleting learned rules
Tools 5
record_errorRecords a correction and saves it as a learned rule with metadata.list_errorsLists all learned rules from the relevant CLAUDE.md file.delete_ruleDeletes a learned rule by index or substring match.update_ruleUpdates an existing rule's text, date, and optionally category.review_rulesReviews all rules with their age for lifecycle management.Try it
Original README from henningziech/claude-error-collector-mcp
Claude Error Collector
An MCP server for Claude Code that learns from your corrections. When you tell Claude "that was wrong" or "no, do it like this", it records the lesson as a rule in your CLAUDE.md - so the same mistake doesn't happen twice.
How It Works
- You correct Claude during a coding session
- Claude recognizes the correction and calls the
record_errortool - The server derives a rule and writes it to the appropriate
CLAUDE.md - Claude reads that rule in future sessions and avoids repeating the mistake
The server automatically detects whether you're in a project directory (writes to project CLAUDE.md) or your home directory (writes to ~/.claude/CLAUDE.md).
Tools
`record_error`
Records a correction and saves it as a learned rule with metadata (date, category).
| Parameter | Type | Required | Description |
|---|---|---|---|
error_description |
string | yes | What was wrong |
correction |
string | yes | What is correct |
rule |
string | yes | Derived guideline, e.g. "ALWAYS use X instead of Y" |
category |
string | no | Rule category (e.g. "n8n", "bash", "google-workspace"). Auto-detected if omitted. |
project_dir |
string | no | Current working directory (for finding project CLAUDE.md) |
`list_errors`
Lists all learned rules from the relevant CLAUDE.md. Supports filtering and grouping.
| Parameter | Type | Required | Description |
|---|---|---|---|
category |
string | no | Filter rules by category |
grouped |
boolean | no | Group rules by category with headings |
project_dir |
string | no | Current working directory |
`delete_rule`
Deletes a learned rule by index or substring match.
| Parameter | Type | Required | Description |
|---|---|---|---|
index |
number | no* | 1-based index of the rule to delete |
match |
string | no* | Substring to match (must match exactly one rule) |
project_dir |
string | no | Current working directory |
*Exactly one of index or match must be provided.
`update_rule`
Updates an existing rule's text, date, and optionally category.
| Parameter | Type | Required | Description |
|---|---|---|---|
index |
number | no* | 1-based index of the rule to update |
match |
string | no* | Substring to match (must match exactly one rule) |
new_rule |
string | yes | The new rule text |
category |
string | no | New category (keeps existing if omitted) |
project_dir |
string | no | Current working directory |
*Exactly one of index or match must be provided.
`review_rules`
Reviews all rules with their age for lifecycle management.
| Parameter | Type | Required | Description |
|---|---|---|---|
older_than_days |
number | no | Threshold in days to consider "old" (default: 30) |
project_dir |
string | no | Current working directory |
Output Format
Rules are stored in a ## Learned Rules section in your CLAUDE.md with metadata as HTML comments:
## Learned Rules
- Legacy rule without metadata (still supported)
### N8n
- Bei n8n IMMER nodeId verwenden
### Bash
- NEVER embed large JSON inline in Bash commands
Metadata fields:
@date:YYYY-MM-DD— when the rule was created/updated@category:name— rule category for grouping
Rules without metadata (legacy format) remain fully supported and appear at the top of the section without a category heading.
Installation
git clone https://github.com/henningziech/claude-error-collector-mcp.git
cd claude-error-collector-mcp
npm install && npm run build
claude mcp add error-collector -s user -- node "$PWD/dist/index.js"
Restart Claude Code after installation. No manual CLAUDE.md editing needed — the server provides its own instructions to Claude via MCP server metadata.
CLAUDE.md Resolution
The server finds the right CLAUDE.md using this logic:
- If
project_diris provided: walk up the directory tree looking forCLAUDE.md - If found and not in the home directory: use it (project-level rules)
- Fallback:
~/.claude/CLAUDE.md(global rules)
Duplicate Detection
Duplicate detection works on two levels:
Server-side: Before writing a rule, the server checks existing rules using case-insensitive substring matching. If the new rule is already covered by an existing one (or vice versa), it skips the write.
Semantic (via instructions): The server instructs Claude to review existing learned rules for semantic equivalence before calling
record_error— even if the wording differs. Claude will:- Skip silently if the rule clearly already exists
- Record it if the rule is clearly new
- Ask the user if a similar rule exists but it's not 100% clear w