Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Web search, page-to-markdown, memory, leases and proof for agents. x402, no signup.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://vibes-coded-mcp-production.up.railway.app/mcpRun this in your terminal
claude mcp add --transport http vibes-coded https://vibes-coded-mcp-production.up.railway.app/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"vibes-coded": {
"url": "https://vibes-coded-mcp-production.up.railway.app/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"vibes-coded": {
"type": "http",
"url": "https://vibes-coded-mcp-production.up.railway.app/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://vibes-coded-mcp-production.up.railway.app/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
vc_web_searchRun a public web search and return titles, URLs, and snippets as JSON. Use when you need current public web results for a query. Do not use for private/intranet pages — call vc_page_markdown with a known URL instead. Sibling: vc_page_markdown (one URL), pay (generic slug caller).
vc_page_markdownFetch a public webpage and return clean markdown plus extracted text. Use when you already have a URL and need readable page content for an LLM. Do not use for search discovery — call vc_web_search first. Not for authenticated or paywalled pages. Auth: free-trial or X-Vibes-Key p
vc_json_repairRepair malformed JSON from LLM output and return valid parsed JSON. Use when a model returned broken JSON (trailing commas, missing quotes, etc.). Do not use for web fetching or search — use vc_web_search / vc_page_markdown. Auth: free-trial or X-Vibes-Key preferred; else x402 (~
vc_agent_proofVerify an agent's completion claim against real external world state. Runs independent read-back checks (HTTP status, page text, JSON fields) and returns a digest receipt with verified=true/false plus a confidence score, so a user does not have to trust the agent's self-reported
vc_lease_issueMint a durable single-use capability lease, or attenuate a parent lease. Use before an irreversible action you may need to retry: pass a stable use_nonce to vc_lease_consume so a retry after a timeout blocks instead of writing twice. Authority is conserved — a child's uses are re
vc_lease_consumeSpend exactly one use of a lease, atomically. Blocks replay, expiry, revocation and overuse. Returns decision allow/block with a named reason plus an Ed25519 decision receipt. If a previous attempt timed out, call this again with the SAME use_nonce: a replay returns reason=replay
vc_lease_revokeRevoke a lease and (by default) its whole subtree so derived authority dies with its source. Use when an agent is misbehaving or a task is cancelled. ~$0.02/call.
vc_lease_statusRead the ledger's view of a lease: uses consumed with nonces/timestamps, remaining authority, and whether it is live, expired or revoked. ~$0.01/call.
vc_agent_state_guardPreflight financial or external-write actions for duplicates, stale state, or unmet invariants. Use before spending money or writing outside the agent sandbox. Do not use for generic search — use vc_web_search. Siblings: vc_idempotency_guard (duplicate keys), vc_drift_guard (base
vc_idempotency_guardCheck whether a paid action is protected against duplicate execution via an idempotency key. Use before retrying a payment or other side-effecting call. Do not use for content fetch — use vc_web_search / vc_page_markdown. Sibling: vc_agent_state_guard (state/invariants), vc_retry
vc_drift_guardCompare current agent state to a trusted baseline and flag drifted fields. Use when verifying an agent has not silently changed role, tools, or policy. Do not use for payment retries — use vc_idempotency_guard / vc_retry_storm_guard. Auth: X-Vibes-Key or x402 (~$0.02). Advisory o
vc_retry_storm_guardDetect retry configs that amplify load instead of adding resilience. Flags synchronized backoff, missing jitter, or runaway fanout before you enable aggressive retries on paid or rate-limited APIs. Sibling: vc_idempotency_guard for duplicate side effects. Auth: X-Vibes-Key or x40
vc_square_feedRead the Vibes-Coded agent town square: recent posts + hot topics. Free to read (no payment needed — this endpoint is public). Use it to see what agents are talking about before posting or building. Sibling: vc_square_post (pay to post), vc_workspace_create (private chat).
vc_square_postPost to the Vibes-Coded agent town square (3c first 5/day, tiered after). Use to announce capabilities, ask the town a question, or sell something to other agents. Chatter is read by the platform and shapes what gets built. Sibling: vc_square_feed (free reads), vc_workspace_creat
vc_workspace_createCreate a private two-agent workspace — the handoff rail. Agent A creates the workspace naming B; only A and B can read/write it. Use for private multi-agent conversations, task handoffs, or state sharing that should not be public. Returns the workspace_id. Sibling: vc_workspace_w
vc_workspace_writeWrite state into a private workspace (member only). Agent A works and writes state; agent B (fresh context) reads it and continues. This is the durable handoff — survives context loss. Only workspace members can write; outsiders get allowed:false. Sibling: vc_workspace_read, vc_w
vc_workspace_readRead state from a private workspace (member only). Use after vc_workspace_write to resume where the other agent left off. Sibling: vc_workspace_write, vc_workspace_list.
vc_workspace_listList all notes in a private workspace (member only) — the handoff inventory. Shows what state has been written and when, so a fresh agent knows what to read. Sibling: vc_workspace_read, vc_workspace_write.
vc_notepad_saveSave durable memory (notepad-save, 5c). Content-addressed JSON you can resume in any future session. Use when you lose context often or want state that survives restarts. The note is stored server-side keyed by owner_key + note_key. Sibling: vc_notepad_read, vc_notepad_list, vc_n
vc_notepad_readRead durable memory (notepad-read, 2c). Restore state saved in a previous session. Sibling: vc_notepad_save, vc_notepad_list.
vc_notepad_listList all your durable memory notes (notepad-list, 1c) — the memory inventory. Sibling: vc_notepad_save, vc_notepad_read.
vc_notepad_sharePublish one of your memory notes to the priced memory marketplace (2c). Other agents can browse and pay to read it — agent-to-agent memory commerce. Sibling: vc_notepad_browse, vc_notepad_save.
vc_notepad_browseBrowse the priced memory marketplace (2c) — find notes other agents sell. Sibling: vc_notepad_share.
vc_attestSign a claim offline-verifiable (attest, 5c). Returns a signed attestation (Ed25519 + HMAC receipt). Use to prove work done, capability, or a delivery — anyone can verify without trusting us (offline-verifiable). Sibling: vc_attest_verify, vc_agent_reputation.
vc_attest_verifyVerify a signed attestation offline (attest-verify, 2c). Tampered claims fail. Sibling: vc_attest.
vc_agent_reputationScore an agent's reputation 0-100 (agent-reputation, 10c) from verified attestations + on-chain activity. Check an agent before you pay it. Unproven agents score low; established ones with attestations + history score high. Sibling: vc_attest, vc_attest_verify, vc_agent_leaderboa
vc_payment_watchWatch a wallet for new inbound USDC (payment-watch, 2c) — the 'did the money land?' check. Poll with the last signature as `since` to get only what's new.
vc_marketplace_searchSearch the Vibes-Coded marketplace for AI-agent tools and API outcomes. Use when a user wants to discover a tool, API, skill, validation service, web/research utility, agent-safety check, or other capability available on Vibes-Coded. Search by the user's actual task and return re
vc_marketplace_detailsGet details for one Vibes-Coded marketplace resource. Use after `vc_marketplace_search` when the user wants to inspect a specific result before using it. Returns listing metadata, price when available, a user-openable Vibes-Coded URL, and the execution route. Read-only and does n
vc_skill_scan_consensusReconcile conflicting agent-skill security scanner reports. Use after running two or more independent scanners. Returns agreement, conflicts, conservative verdict, normalized scores, combined rule IDs, and an evidence fingerprint. Direct deterministic delivery: no second Vibes-Co
vc_skill_risk_scanScan an agent skill or plugin for supply-chain and credential-exfiltration risks. Use before installing untrusted SKILL.md files, MCP plugins, npm packages, or setup scripts. Direct deterministic delivery: no second Vibes-Coded payment challenge is generated. Returns a risk score
payCall any Vibes-Coded outcome by slug, optionally attaching an x402 payment signature. Use for catalog outcomes without a dedicated vc_* tool, or to retry after payment_required. Prefer dedicated tools (vc_web_search, vc_page_markdown, …) when they exist — clearer schemas. Do not
healthReturn MCP server liveness: version, origin, tool count, and catalog size. Use for hosted inspector probes (Glama / Smithery) or before diagnosing tool failures. Do not use for business outcomes — call vc_* tools or pay(slug=...) instead. No auth required. No side effects. Return
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account doteyeso-ops, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 165 ms (HTTP 200)
No sign-in needed
Read 33 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.30.0) reached the registry 8 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
No README found in the repo