AgentPool
PYPI · AGENTPOOL-CLI
See each coding-agent subscription's live limits and offload work to one with headroom.
Available components
Last scanned (18 hours ago)
Scores higher than 84% of PyPI servers
Category Developer Tools
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 3 of 37 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to sidduHERE/agentpool). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 134 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability43
- 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 1101 tokens (~57/item across 19 items; 16 tools + 3 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
- Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 18 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
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 5 Nov 26 −5
- Stability: pass → 0.67 functional
- 30 Oct 26 0
- Stability: 0.97 → pass security
- 29 Oct 26 0
- Stability: pass → 0.97 functional
- 23 Oct 26 0
- Stability: 0.97 → pass security
- 22 Oct 26 0
- Stability: pass → 0.97 functional
- 16 Oct 26 +37
- Injection markers: unverified → pass ▲ security
- Stability: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Schema quality: unverified → 0 ▲ functional
- 12 Oct 26 −36
- Stability: 0.93 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 0 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- 7 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 93. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
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 5 Nov 2026 · Analysed pypi/agentpool-cli@0.1.13
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | sidduHERE/agentpool |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/sidduHERE/agentpool/.github/workflows/release.yml@refs/tags/v0.1.13 |
| Rekor log index | 1933886659 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:e539d2092dc5af9d3e95342e7265e16df349b3289179d292ed3ef6ed59f5773c |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 37 packages
| Packages resolved | 37 |
|---|---|
| Stale | 3 |
| 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 →
collect_worker_artifacts Collect Worker Artifacts ~77
AgentPool worker lifecycle collect artifacts before terminate cleanup: result, transcript, events, git diff, and runtime artifacts after observe/poll.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
| include_diff | boolean | – | – |
| include_transcript | boolean | – | – |
| mark_completed | boolean | – | – |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
get_artifact_manifest Get Artifact Manifest ~36
AgentPool artifact manifest: list stored files for a worker session without inlining worker text.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
No output schema declared.
No examples provided.
get_cached_usage_snapshot Get Cached Usage Snapshot ~34
Compatibility alias for cached get_usage_snapshot(refresh=false): read persisted provider usage without live probes.
| Name | Type | Req | Description |
|---|---|---|---|
| provider_id | – | – | – |
No output schema declared.
No examples provided.
get_capacity_summary Get Capacity Summary ~58
Compatibility alias for get_usage_summary. Use for AgentPool capacity, quota, and provider headroom checks.
| Name | Type | Req | Description |
|---|---|---|---|
| backend | string | – | – |
| provider_id | – | – | – |
| refresh | boolean | – | – |
| timeout_seconds | number | – | – |
No output schema declared.
No examples provided.
get_delegation_preferences Get Delegation Preferences ~31
AgentPool delegation preferences from the user: when to use workers, preferred providers, and safety posture.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_inventory Get Inventory ~38
AgentPool provider inventory: installed CLIs, auth, runtime support, models, and optional cached usage state.
| Name | Type | Req | Description |
|---|---|---|---|
| include_usage | boolean | – | – |
No output schema declared.
No examples provided.
get_provider_models Get Provider Models ~38
AgentPool provider model catalog lookup, including Cursor Composer models, Codex models, Claude models, and configured aliases.
| Name | Type | Req | Description |
|---|---|---|---|
| provider_id | – | – | – |
No output schema declared.
No examples provided.
get_usage_snapshot Get Usage Snapshot ~58
AgentPool raw usage snapshots. Defaults to SQLite cache; refresh is bounded and non-interactive in MCP.
| Name | Type | Req | Description |
|---|---|---|---|
| backend | string | – | – |
| provider_id | – | – | – |
| refresh | boolean | – | – |
| timeout_seconds | number | – | – |
No output schema declared.
No examples provided.
get_usage_summary Get Usage Summary ~61
AgentPool usage and capacity summary: provider headroom, quota windows, usable status, and cached or bounded refreshed usage.
| Name | Type | Req | Description |
|---|---|---|---|
| backend | string | – | – |
| provider_id | – | – | – |
| refresh | boolean | – | – |
| timeout_seconds | number | – | – |
No output schema declared.
No examples provided.
interrupt_worker Interrupt Worker ~30
AgentPool interrupt worker: send an interrupt to a running worker session.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
No output schema declared.
No examples provided.
observe_worker Observe Worker ~75
AgentPool worker lifecycle observe worker: wait for state, questions, approval prompts, completion, errors, and readiness.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
| include_recent_log | boolean | – | – |
| max_lines | – | – | – |
| session_id | string | yes | – |
| timeout_seconds | integer | – | – |
| wait_for | – | – | – |
No output schema declared.
No examples provided.
poll_worker Poll Worker ~56
AgentPool worker lifecycle poll worker: return current state and optional recent log tail without waiting.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | – |
| include_recent_log | boolean | – | – |
| max_lines | – | – | – |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
read_worker_transcript Read Worker Transcript ~57
AgentPool read worker transcript: bounded transcript pages, with lockdown support for untrusted worker text.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
| session_id | string | yes | – |
| tail_lines | – | – | – |
No output schema declared.
No examples provided.
send_worker_message Send Worker Message ~49
AgentPool send worker message: steer an existing worker session and submit the text when requested.
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | – |
| session_id | string | yes | – |
| submit | boolean | – | – |
No output schema declared.
No examples provided.
spawn_worker Spawn Worker ~146
AgentPool spawn worker: start one explicit provider CLI session, such as cursor-cli composer-2.5, codex-cli, or claude-code.
| Name | Type | Req | Description |
|---|---|---|---|
| account | – | – | – |
| allowed_files | – | – | – |
| initial_prompt_mode | string | – | – |
| isolation | string | – | – |
| max_runtime_seconds | – | – | – |
| max_turns | – | – | – |
| metadata | – | – | – |
| model | – | – | – |
| provider_id | string | yes | – |
| reasoning_effort | – | – | – |
| repo_path | string | yes | – |
| role | string | – | – |
| runtime | – | – | – |
| service_tier | – | – | – |
| supervision | string | – | – |
| task | string | yes | – |
No output schema declared.
No examples provided.
terminate_worker Terminate Worker ~42
AgentPool worker lifecycle terminate worker cleanup: stop the selected runtime session and mark it cancelled when still active.
| Name | Type | Req | Description |
|---|---|---|---|
| reason | – | – | – |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
How do I install the AgentPool MCP server?
AgentPool runs locally as a PyPI package, launched with uvx agentpool-cli mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · agentpool-cli
claude mcp add sidduhere-agentpool -- uvx agentpool-cli mcp
What is the AgentPool MCP server?
AgentPool is an MCP server listed in the public MCP registry as io.github.sidduHERE/agentpool. See each coding-agent subscription's live limits and offload work to one with headroom. This page covers its PyPI package (agentpool-cli).
Is the AgentPool MCP server safe to use?
AgentPool scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. 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 AgentPool MCP server expose?
AgentPool exposes 16 tools: get_inventory, get_usage_snapshot, get_cached_usage_snapshot, get_usage_summary, get_capacity_summary, and 11 more. Their descriptions and schemas cost roughly 886 tokens of context every time the server is loaded.
Is the AgentPool MCP server still maintained?
AgentPool is still listed as active in the MCP registry. We last reached this channel on 5 November 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 AgentPool MCP server under?
AgentPool declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the AgentPool MCP server?
VerifyMCP ran 16 checks on AgentPool, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.