Confirm whether the server label matches its reach
Weak labeling should be easy to notice when a server is broadly shared.
QI
MCP Servers Detail
An MCP server detail page should make one server legible as a tool surface: who uses it, what it exposes, what transport it runs on, and where reliability or reach becomes risky.
Use This Page When Asking
How much reach does this tool surface create, and what makes it ordinary or concerning?
Open c6 raw detailConnected sessions
18
Broad reuse across work
Tools exposed
8
Most-used capability surface
Top tool
read_file
318 calls
Health posture
stable
0.2% error rate
Why This Detail Matters
Important Metadata
Server
filesystem
Version
1.0.0
Transport
stdio
URL
local process
Client
Claude Code
Protocol Version
2025-03-01
What This Detail Should Help Decide
Check top-tool demand before looking at long tool tables
A small tool cluster usually explains the server faster than a complete invocation list.
Use connected sessions to validate caller fit
The page should make unexpected reuse feel clearly out of pattern.
MCP Server-Centered Topology
An MCP server map should expose caller demand, tool surface, transport, and operational health.
Useful per server: which agents connect to it, how many tools it exposes, what sessions depend on it, where transport or latency adds risk, and what failures cluster around it.
MCP Server
filesystem v1.0.0
Broadly shared server whose tools shape the majority of code-oriented sessions.
18 sessions · 420 calls
Transport
http
Tool surface
8 tools
Avg posture
0.2% error rate
Blast radius
shared by multiple agents
Callers
Who depends on this server.
Claude Codeprimary agent
Cursorsecondary agent
alice@company.comfrequent user
Tool Surface
Which exposed tools matter most.
read_file318 calls
write_file204 calls
list_directory191 calls
Execution Context
Operational details that explain behavior.
http transportnetworked
local filesystemasset reach
todaylast seen
Watch For
Where health and risk can degrade.
web-search 3.4%compare error outlier
latency drifttool slowdown
unexpected callernew client
Representative Event Chain
The page should show how the item participates in a readable sequence, not just a pile of supporting rows.
- 1
Surface creation
A server becomes a reusable access surface
The server first matters because several agent and user lanes depend on it for the same family of actions.
filesystemClaude CodeCursor - 2
Tool concentration
A small set of tools explains most of its real reach
Top tools should stay near the server identity so the reviewer sees capability, not just transport metadata.
read_filewrite_filelist_directory - 3
Trust change
Transport and health shift how broadly the surface should be trusted
Unclear business purpose, error spikes, or unexpected callers turn a familiar server into a review target.
http transportunexpected callerlatency drift - 4
Verification
The reviewer pivots into sessions or the raw tool ledger
Once the surface is understood, the raw tables help verify whether the current demand pattern matches the expected one.
raw listsession detail
c6 Evidence Tables
Tools Exposed
The raw detail emphasizes the actual reachable tool surface.
| Tool | Invocations | Error rate | Avg latency |
|---|---|---|---|
| read_file | 48 | 0.0% | 95ms |
| edit_file | 14 | 0.0% | 110ms |
| list_dir | 8 | 2.3% | 124ms |
Sessions Connected
c6 then connects the server back to real usage lanes.
| User | Agent | Tool calls | Status |
|---|---|---|---|
| alice@company.com | Claude Code | 22 | active |
| carol@company.com | Claude Code | 9 | active |
| ci-runner-04 | LangChain | 4 | ended |
Return To Category
Compare this representative detail against the full category framing and drill targets.
Open MCP Servers overviewOpen c6 Raw Detail
Use the original detail page for exact raw evidence after the c12 story framing.
Open c6 raw detailOpen c6 Raw List
Compare this item against the broader c6 entity ledger once the representative story is clear.
Open c6 raw list