list_categories
List the eight problem categories
The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them. Start here to see what exists.
Takes no parameters.
ContextOverflow
org.contextoverflowPublished by contextoverflow.orgOfficial publisherv1.0.0Updated Oct 24, 2026
Describe what's going wrong with your AI; get the named technique both of you can read. No auth.
Overview
AI-generated overview
A free, keyless remote MCP server that matches a described AI thinking problem to named context-engineering techniques and returns runnable scaffolds.
- What you can do
- List the problem categories the corpus covers, phrased as human complaints about AI behavior, and classify a symptom description into matching techniques, asking one clarifying question when ambiguous. Look up a technique directly by id or name. Read a technique's mechanism, agent instructions, narration template, verification check and failure modes. Get a minimal executable scaffold with steps, a narration line to say to the user, and a check that proves it worked.
- When to use it
- Useful when an assistant or its user wants to name and correct a recurring working problem, such as losing context, over-agreeing, stalling, or doing more than asked, and wants a structured technique with a verification step rather than a generic prompt tip.
- Requirements
- Remote Streamable HTTP endpoint at contextoverflow.org; no authentication, API key or environment variables declared. Network access is required.
Before you install
The server is stateless and keyless, so no credentials are exposed. Responses include narration lines and instructions meant to be spoken to the user, and apply_technique returns scaffolds the assistant may act on; review those before running them. Descriptions of problems are sent to a third-party service.
Installation
In SourceWeft
- Open ContextOverflow in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/org.contextoverflow%2Flibrary/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"contextoverflow": {
"type": "http",
"url": "https://contextoverflow.org/mcp"
}
}
}README
Context Overflow
Like Stack Overflow, but for context engineering — thinking techniques for humans and AI agents, from one corpus, through two doors.
Most guides teach you to write better prompts. Context Overflow teaches something different: how to work with AI so that it extends your thinking instead of replacing it — and gives your agent the same techniques through a protocol it can actually run.
The two doors
For humans — contextoverflow.org. A curated, categorized corpus of thinking techniques. No login, no feed. You arrive with a problem — the site opens with "What's going wrong?" — find the technique that fits, and learn to build it into a prompt yourself: worked, annotated examples, never copy-paste snippets. The research reference for what this counters: contextoverflow.org/cognitive-debt.
For agents — MCP at contextoverflow.org/mcp. The same corpus served over Streamable HTTP; free, keyless, stateless. Listed in the official MCP Registry as org.contextoverflow/library. Five tools:
Every response carries a narration line, so the agent's technique use surfaces in-conversation in the same vocabulary its human learned on the site. When your agent says "one real unknown before I act," you know exactly which technique is running. Both sides of the pair get smarter; neither goes opaque. Setup for every client: contextoverflow.org/connect.
The major problem categories we've found so far
lost-the-thread · doing-my-thinking · confidently-wrong · agrees-with-everything · stalls-instead-of-acting · bloated-answers · starting-blind · problem-too-big · faster-than-i-can-review · did-more-than-i-asked · dumber-after-the-update
Each named for the problem as you experience it — "My AI forgets everything between sessions," "It tells me I'm right even when I'm not." Every technique lives in exactly one, and answers it.
What makes an entry
Entries are grounded in real production use (generalized field notes) or published research (verified citations only — an unverifiable attribution doesn't ship). Every entry states its mechanism, its verification check, and its failure modes — if we can't tell you how to know it worked, it doesn't ship. The full contract: corpus/SCHEMA.md.
Repository layout
corpus/— the techniques. The repo is the database; site and MCP are two views of it.site/— the human door: Jekyll, generated from the corpus at build time.mcp/— the agent door: a stateless TypeScript Cloudflare Worker, corpus compiled in, no LLM inside.validator/— the gate both doors build behind: schema, section order, edge integrity, and a build-failing privacy blocklist.
Contributing
See CONTRIBUTING.md. Short version: the front door is the suggestion box — propose techniques, vote on what gets built next; issues are open for evidence-based disagreement. Corpus and code PRs aren't accepted right now; every entry that ships passes the validator and carries real evidence.
License
corpus/— CC BY-NC-ND 4.0- everything else — Elastic License 2.0
Why these licenses. Context Overflow is free to read, learn from, and use — by people and by their AI. AI crawlers are welcome, and the corpus is served live to agents over MCP, because a shared vocabulary between a human and their assistant is the entire point. What the licenses reserve is commercial repackaging: the corpus may not be rebundled or sold as a competing product (NC-ND), and the code may not be offered as a hosted service (Elastic 2.0). Learn it, teach it to your agent, build it into your prompts — just don't repackage it.
Source: README.md at commit 6772805
Tools
5classify_intent
Match a problem description to techniques
Describe what's going wrong — your human's complaint, or a failure you notice in your own behavior — and get the matching techniques. Deterministic matching; if the description fits two problems it returns one clarifying question instead of guessing.
Parameters
descriptionrequiredfind_technique
Look up a technique by name
Direct lookup by technique id or name, for when you already know what you want. To match by symptom, use classify_intent instead.
Parameters
queryrequiredget_technique
Learn a technique
A technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice. The full human page is linked, not inlined.
Parameters
idrequiredapply_technique
Run a technique now
The minimal executable scaffold: steps (or self-diagnostic for anti-patterns), the narration line to say to your human, and the verification check that proves it worked.
Parameters
idrequiredVersion history
1- v1.0.0LatestSep 16, 2026
Score
90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.