Agentic Observability MCP
NPM · AGENTIC-OBSERVABILITY-MCP · SCANNED SEP 25
Agent tracing, cost tracking, anomaly detection for LLM agents
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 154 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability42
- 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 589 tokens (~73/item across 8 items; 6 tools + 2 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Agentic Observability MCP server?
Agentic Observability MCP runs locally as an npm package, launched with npx -y agentic-observability-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · agentic-observability-mcp
claude mcp add mdfifty50-boop-agentic-observability -- npx -y agentic-observability-mcp
{
"mcpServers": {
"mdfifty50-boop-agentic-observability": {
"command": "npx",
"args": [
"-y",
"agentic-observability-mcp"
]
}
}
} {
"servers": {
"mdfifty50-boop-agentic-observability": {
"command": "npx",
"args": [
"-y",
"agentic-observability-mcp"
]
}
}
} codex mcp add mdfifty50-boop-agentic-observability -- npx -y agentic-observability-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mdfifty50-boop-agentic-observability": {
"type": "local",
"command": [
"npx",
"-y",
"agentic-observability-mcp"
],
"enabled": true
}
}
} openclaw mcp add mdfifty50-boop-agentic-observability --command npx --arg -y --arg agentic-observability-mcp
mcp_servers:
mdfifty50-boop-agentic-observability:
command: "npx"
args: ["-y", "agentic-observability-mcp"] {
"McpServers": {
"mdfifty50-boop-agentic-observability": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"agentic-observability-mcp"
]
}
}
} assistant mcp add mdfifty50-boop-agentic-observability -t stdio -c npx -a -y agentic-observability-mcp
{
"mcpServers": {
"mdfifty50-boop-agentic-observability": {
"command": "npx",
"args": [
"-y",
"agentic-observability-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 25 Sept 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 −3
- Stability: pass → 0.80 functional
- 23 Sept 26 0
- Stability: 0.97 → pass security
- 22 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −3
- Security disclosure: unverified → fail ▼ functional
- Stability: pass → 0.80 functional
- 16 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Sept 2026 · Analysed npm/agentic-observability-mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
detect_anomaly ~61
Flag unusual patterns in agent behavior: cost spikes, high error rates, latency issues, infinite loops, and token explosions.
| Name | Type | Req | Description |
|---|---|---|---|
| check_types | array | yes | Types of anomaly checks to run |
| session_id | string | yes | Session ID to check for anomalies |
No output schema declared.
No examples provided.
get_cost_report ~75
Get cost breakdown across multiple sessions, grouped by model, provider, tool, or session. Supports time range filtering.
| Name | Type | Req | Description |
|---|---|---|---|
| group_by | string | yes | How to group the cost breakdown |
| session_ids | array | – | Specific session IDs to include (defaults to all) |
| time_range | object | – | Filter by time range |
No output schema declared.
No examples provided.
get_session_summary ~47
Get a comprehensive cost and performance summary for an agent session, including token usage, tool call stats, and model breakdown.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | Session ID to get summary for |
No output schema declared.
No examples provided.
log_tool_call ~125
Log an MCP tool call with performance data including latency, success/failure, and error details.
| Name | Type | Req | Description |
|---|---|---|---|
| error | string | – | Error message if call failed |
| latency_ms | integer | yes | Call latency in milliseconds |
| params | object | yes | Parameters passed to the tool |
| result_summary | string | – | Brief summary of the result |
| server_name | string | yes | Name of the MCP server |
| session_id | string | yes | Unique session identifier |
| success | boolean | yes | Whether the call succeeded |
| tool_name | string | yes | Name of the tool called |
No output schema declared.
No examples provided.
trace_agent_action ~115
Log an agent action with metadata for audit trails and debugging. Supports tool calls, LLM requests, decisions, and errors.
| Name | Type | Req | Description |
|---|---|---|---|
| action_type | string | yes | Type of action being traced |
| description | string | yes | Human-readable description of the action |
| metadata | object | – | Additional key-value metadata |
| session_id | string | yes | Unique session identifier |
| timestamp | string | – | ISO 8601 timestamp (defaults to now) |
| tool_name | string | – | Name of the tool (for tool_call actions) |
No output schema declared.
No examples provided.
track_token_usage ~152
Track token usage and cost for an LLM call. Auto-calculates cost from built-in pricing table if per-token costs are not provided.
| Name | Type | Req | Description |
|---|---|---|---|
| cost_per_input_token | number | – | Cost per input token (overrides built-in pricing) |
| cost_per_output_token | number | – | Cost per output token (overrides built-in pricing) |
| input_tokens | integer | yes | Number of input/prompt tokens |
| model | string | yes | Model name (e.g., claude-sonnet-4, gpt-4o) |
| output_tokens | integer | yes | Number of output/completion tokens |
| provider | string | yes | LLM provider |
| session_id | string | yes | Unique session identifier |
No output schema declared.
No examples provided.
What is the Agentic Observability MCP server?
Agentic Observability MCP is listed in the public MCP registry as io.github.mdfifty50-boop/agentic-observability. Agent tracing, cost tracking, anomaly detection for LLM agents. This page covers its npm package (agentic-observability-mcp).
Is the Agentic Observability MCP server safe to use?
Agentic Observability MCP scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Agentic Observability MCP server expose?
Agentic Observability MCP exposes 6 tools: trace_agent_action, track_token_usage, log_tool_call, get_session_summary, detect_anomaly, get_cost_report. Their descriptions and schemas cost roughly 575 tokens of context every time the server is loaded.
Is the Agentic Observability MCP server still maintained?
Agentic Observability MCP is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Agentic Observability MCP server under?
Agentic Observability MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.