conxt
Description
Persistent AI memory layer for developers. Never re-explain your stack to AI tools again. Conxt captures your decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf — and surfaces them automatically at the start of every new session. **8 MCP tools:** - [get_context](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:223:0-255:52) — load relevant memories for the current task - [get_memories](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:258:0-351:53) — list memories with type/source/date filters - [get_pinned](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:390:0-412:60) — fetch your pinned memories - [search_decisions](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:354:0-387:53) — search decisions and coding rules by topic - [add_memory](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:415:0-457:47) — s
What our measurements say
conxt is a remote MCP server published at mcp.conxt.dev. It has been probed 7 times since 9/10/2026. It answered in only 6 of them (85.7%), indicating low availability. Median response time is 495 ms, placing it among the faster endpoints. It exposes a broad tool surface of 17 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names like 'add_team_memory' and 'set_memory_status' clearly indicate their purpose.
- Some tools (e.g., 'add_memory') include detailed parameter guidelines in descriptions.
Weaknesses
- Descriptions for tools like 'list_my_teams' are cut off mid-sentence, losing critical usage context.
- Parameter requirements (required/optional) are unclear in most tools (e.g., 'search_decisions' lacks explicit parameter definitions).
- Tools like 'get_context' and 'get_memories' risk overlap in functionality without clear differentiation.
list_my_teams— Description truncated mid-sentence, missing critical usage details.search_decisions— No explicit parameter requirements or types specified.resolve_context— Ambiguous purpose compared to 'search_memory' and 'get_context'.
Verdict
Event narrative
Risk: medium
- 2026-09-10T21:16:35.016Z — Era changed from unspecified to 'auth-gated', complianceScore became null · Indicates potential configuration shift with compliance data loss
- 2026-09-11T01:59:45.474Z — Era changed from 'auth-gated' to 'legacy', complianceScore improved from null to 100 · Successful transition with full compliance validation achieved
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test failed · last run:
- Cold-start: cold 123ms → warm 129ms (penalty 0ms)
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Server build: — → 1.27.1
- Back up
- Became unreachable
- Incomplete probe — one leg did not answer, era result not counted
- Server build: — → 1.27.1
- Supported versions: — → 2025-11-25
- Era changed: Auth-gated → Legacy
- Added to watch — era: Auth-gated
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/pgavali0318-conxt)<a href="https://mcpmetrics.io/servers/pgavali0318-conxt"><img src="https://mcpmetrics.io/badge/pgavali0318/conxt/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see