Local-first durable AI memory with policy-bound recall and a typed project graph.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 19,225–19,248 of 165,917 resultsPage 802 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Share one project context across ChatGPT, Claude, Telegram and any MCP client.
Search and load AI datasets, prompts and few-shot contexts from the ContexteTech catalogue.
Search and load AI datasets, prompts and few-shot contexts from the ContexteTech catalogue.
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
Contextflo connects your data sources (Postgres, Snowflake, BigQuery, Redshift, MySQL, ClickHouse, Databricks) to Claude with a managed context layer, access controls, and query visibility. Your team asks questions in natural language, Contextflo provides the business context and governance so the answers are accurate and consistent. No MCP config or YAML to maintain.
Efficient context management: code search, evidence packs, and memory for coding agents.
Contextick is a personal knowledge layer for your AI. Save any text once — a decision, an idea, a code snippet, research notes — and the AIs you connect can bring it back later by meaning, right when it's relevant. Because your knowledge lives in one private store instead of inside a single assistant, it follows you across every MCP-compatible assistant you connect. Save something in one, recall it in another. There's nothing to organize: no folders, no tags. You just save, and a short bit of context surfaces the closest match when you ask. Use it to keep working decisions, team conventions, preferences, and anything you'd rather not explain to your AI twice.
Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.
Search, browse and read your Contextli voice notes and transcriptions from any MCP client.
A project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.
Team metric definitions for data agents. Learns from corrections, tracks SQL answer accuracy.
Context exoskeleton for AI development: reduce token usage and context occupancy.
Describe what's going wrong with your AI; get the named technique both of you can read. No auth.
Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.
Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.
ContextSMS MCP connects Claude to your ContextSMS SMS business lines. Sign in with your ContextSMS account to work with the phone numbers and conversations your organization has already provisioned in ContextSMS. What you can do: • Read SMS threads and list recent conversations for a customer or business line • Send a single SMS from an authorized ContextSMS line (with built-in rate limits and guardrails) • Check which business lines and agent context you are authorized to use • Poll or wait for new inbound customer messages when you need real-time replies Who it is for: Teams that use ContextSMS for compliant business SMS and want to summarize threads, draft replies, or send one-off messages from Claude without leaving the chat. Requirements: • An active ContextSMS account with at least one authorized business SMS line • OAuth sign-in through ContextSMS (each user connects their own account) Data access: The connector only accesses SMS data and business lines tied to the signed-in ContextSMS user. Messages are not shared across tenants.
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
Project memory, semantic code search, and grounded agent context.
Project memory, semantic code search, and grounded agent context.
MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.
What this catalog covers
- Source listings
- 167,897
- Candidate groups
- 168,273
- Setup-eligible endpoints
- 30,743
Sources observed 2026-10-24–2026-11-12. Listings can overlap across sources. Groups are identity candidates; setup eligibility is not a successful connection test.
SourcesMCP data from Glama connectorsMCP data from Glama source codeOfficial MCP RegistryClaude connector directoryAPI Tracker · publisher documentationSlack MCP directory
Default browsing excludes 2,356 specialized utility groups across the catalog. They remain available through keyword search and direct links. This editorial filter does not change the indexed totals or establish publisher quality.
Categories currently cover records matched to our reviewed catalog; other listings remain Uncategorized. Source-only projects have no generated connection option. Browse reviewed official MCPs →
- Glama connectors
API result set; pagination may cap at approximately 1,000 connectors. Not exhaustive.
- Glama source code
Complete chronological source-code catalog response; includes source-reported author classifications, not publisher attestations or ready-to-use endpoints.
- Official MCP Registry
Complete paginated registry response; registry membership is not publisher verification.
- Claude connector directory
Complete public Claude directory MCP components. Source tiers, tools, icons and sign-in hints are declarations, not publisher or runtime verification.
- API Tracker · publisher documentation
Reviewed publisher and third-party remote, local and setup-only MCP listings. Publisher status is retained per exact connection. Discoverability does not establish connection readiness.
- Slack MCP directory
Reviewed additions discovered through the public Slack Marketplace MCP category. Complete discovery inventory is retained separately; membership does not prove external-client compatibility.
Listings are grouped by exact public endpoints, exact package sets, or explicit reviewed identity bindings. Shared names or repositories alone do not merge implementations. Official includes publisher evidence and accepted source author classifications. It does not mean independently verified, runtime-tested or security-certified.