pod
Other formats agents might prefer:
markdownjsonllms.txt

Agent? You probably want markdown or json, or Pod over MCP.

Reported issues for Python Docs MCP Server

Pod holds 16 of 33 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to Python Docs MCP Server.

Most discussed

[v0.5.0] benchmark adapters — define OpenAI/Google model matrix

Context

Parent: #63. Methodology: docs/benchmarks/PUBLIC-BENCHMARK-METHODOLOGY.md.

Aymen explicitly wants OpenAI and Google model families included. This issue defines the model/client matrix and provider adapter contracts without letting model choice blur into a single fake tool-quality score.

Goal

Add the benchmark model matrix and provider adapter contracts for OpenAI and Google-backed runs, with tests that use mocks rather than paid/live calls.

Acceptance criteria

  • The

Read the thread · 2026-06-08 · closed · 3 comments

[v0.5.0] benchmark tokens — Claude token-count integration after client rewrap (live-phase-gated)

Context

Parent: #63. Methodology: docs/benchmarks/PUBLIC-BENCHMARK-METHODOLOGY.md (work package 6; "Token Measurement" section). Roadmap decision 5.8: Claude tokenizer, measured after client-side rewrap. Maintainer decision on record (PLAN.md Amendment 2026-07-08): the Anthropic count-tokens API is the counting mechanism, confined to the maintainer-run live phase — exact counts for headline claims, zero runtime network access or new dependencies in the server itself. Token records (mer

Read the thread · 2026-07-08 · closed · 2 comments

[v0.5.0] benchmark adapters — competitor MCP tool adapters (Context7, GitMCP, DeepWiki, Ref.tools)

Context

Parent: #63. Methodology: docs/benchmarks/PUBLIC-BENCHMARK-METHODOLOGY.md (work package 4, real-adapter half — #72 delivered the manifest format; #85 delivered LLM-provider adapters, which are a different axis). Eligibility rules and candidate set (Context7, GitMCP, DeepWiki, Ref.tools) live in the methodology's "Systems Under Test" section.

Status: NOT agent-ready. Filed by the orchestrator per PLAN.md T6(b); Vision must review, pin the competitor versions/endpoints, create t

Read the thread · 2026-07-08 · closed · 2 comments

[v0.5.0] benchmark corpus — mechanical slice: schema, validator, placeholder fixture (split from #71)

Context

Mechanical slice split out of #71 under maintainer approval (D4 in the 2026-07-08 gate record, sign-off mirrored on #63). #71's question authorship and quality review remain permanently the maintainer's; this issue delivers only the schema, the validator, and a clearly-synthetic placeholder fixture so #88 (correctness scorer) can unblock without waiting for the full 50-question corpus.

Hard boundary: docs/benchmarks/corpus.yml is the canonical path reserved for the human-autho

Read the thread · 2026-07-08 · closed · 1 comment

[v0.5.0] docs — write docs/architecture/DESIGN.md (eight-layer design document)

Context

Roadmap §4 assigns v0.5.0 "docs/architecture/DESIGN.md | 5-page design document tying the ADRs together." The eight layers (principle 2.7, enumerated in ADR-006: source connector, ingestion, storage, retrieval, budget, serializer, cache, transport) map to eight planned ADRs, of which four exist or are in flight this run: ADR-001 (source adapters), ADR-006 (serialization), ADR-007 (cache), ADR-008 (transport). ADR-002–005 (ingestion, storage, retrieval, budget) belong to unshipped v

Read the thread · 2026-07-08 · closed · 1 comment

[v0.5.0] docs — write ADR-008 (Transport)

Context

Roadmap §4 assigns v0.5.0 "ADRs 7 and 8 | Cache, Transport." ADR-008 documents the transport layer (layer 8 of the eight-layer contract, principle 2.7). The strict template is the exact skeleton shared by docs/architecture/ADR-001-source-adapters.md and docs/architecture/ADR-006-serialization.md. This is a writing task: every claim must match the code; you are recording the shipped decision, not making new ones.

Maintainer sign-off for this issue's filing: D3 in the 2026

Read the thread · 2026-07-08 · closed · 1 comment

[v0.5.0] docs — write ADR-007 (Cache)

Context

Roadmap §4 assigns v0.5.0 the "Architecture Documentation & Launch" deliverables, including "ADRs 7 and 8 | Cache, Transport." ADR-007 documents the cache layer (layer 7 of the eight-layer contract, principle 2.7). The house template is the exact skeleton shared by docs/architecture/ADR-001-source-adapters.md and docs/architecture/ADR-006-serialization.md — those two files ARE the strict template (roadmap §9.1: "Agent w/ strict template"). This is a writing task: every cl

Read the thread · 2026-07-08 · closed · 1 comment

[v0.5.0] benchmark scoring — correctness scorer with manual-adjudication hooks

Context

Parent: #63. Methodology: docs/benchmarks/PUBLIC-BENCHMARK-METHODOLOGY.md (work package 5; "Correctness Scoring" section defines the 1.0/0.5/0.0 rubric). Runner scoring records (merged #75) already carry score: None + requires_manual_scoring: True placeholders and included_in_correctness_denominator.

Status: NOT agent-ready. Filed by the orchestrator per PLAN.md T6(b); Vision must review, create the .planning/agent-context/ file (decision 5.14, mirrored as an issue com

Read the thread · 2026-07-08 · closed · 1 comment

Most recent

[v0.5.0] benchmark reporting — generate raw report and README-safe summary

Context

Parent: #63. Methodology: docs/benchmarks/PUBLIC-BENCHMARK-METHODOLOGY.md.

The benchmark must produce public-facing output that is credible, boringly auditable, and impossible to confuse with hand-picked marketing numbers.

Goal

Add benchmark reporting that converts raw run artifacts into a full report plus a README-safe summary block gated on reproducible data.

Acceptance criteria

  • README-safe summaries present strict tool + model pairings, for example `python-docs-

Read the thread · 2026-06-08 · closed · 1 comment

[v0.5.0] benchmark runner — add reproducible CLI and artifact layout

Context

Parent: #63. Methodology: docs/benchmarks/PUBLIC-BENCHMARK-METHODOLOGY.md.

This is an agent-ready plumbing issue. The runner should make the benchmark reproducible from the shell without deciding the corpus or claiming results.

Goal

Add a reproducible benchmark runner CLI that loads a corpus and competitor manifest, executes configured benchmark cells, and writes raw artifacts in a stable layout.

Acceptance criteria

  • A tool failure, timeout, or MCP protocol crash on

Read the thread · 2026-06-08 · closed · 1 comment

[v0.5.0] benchmark corpus — define schema and 50-question eval pack

Context

Parent: #63. Methodology: docs/benchmarks/PUBLIC-BENCHMARK-METHODOLOGY.md.

This is the human-led corpus issue. The public benchmark is only credible if the question set is fixed, balanced, version-aware, and auditable before results are known.

Goal

Define the benchmark corpus schema and the 50-question Python stdlib evaluation pack used by the v0.5.0 public benchmark.

Acceptance criteria

  • docs/benchmarks/corpus.schema.json defines the corpus shape: stable ID, cate

Read the thread · 2026-06-08 · open · 0 comments

[v0.3.0] ingestion — pin CPython source by commit SHA

Context

Read the thread · 2026-05-29 · closed · 0 comments

[v0.3.0] docs — write ADR-001 (Source Adapters)

Context

Read the thread · 2026-05-29 · closed · 0 comments

[v0.3.0] docs — write ADR-006 (Serialization)

Context

Goal

Record the already-l

Read the thread · 2026-05-29 · closed · 0 comments

[v0.3.0] security — audit and document PyYAML safe-loader discipline

Context

Read the thread · 2026-05-29 · closed · 0 comments

[v0.3.0] docs — refresh public surfaces to the 6-tool surface

Context

Read the thread · 2026-05-29 · closed · 0 comments

The remaining reports are on the project's issue tracker.