# Reported issues for camt053-mcp

Pod holds 8 of 8 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 [camt053-mcp](/mcp/camt053-mcp).

## Most discussed

### feat(mcp): D7 HTTP/SSE transport + bearer token + Camt053-Account tenant header

Spun off from #17. D1-D6 shipped in v0.0.6/v0.0.7; D7 needs an HTTP/SSE transport variant (stdio doesn't carry HTTP headers) which is a substantial sister change-set.

## What's needed

1. transport=stdio|http CLI flag (FastMCP supports both natively).
2. Bearer-token middleware on the HTTP transport.
3. Optional Camt053-Account header forwarded into a Context field tools can read for multi-tenant scoping.
4. Service-name + scope into the audit log so multi-tenant calls are attributable.
5. Test

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/42) · 2026-06-22 · closed · 1 comment

### v0.0.6 Section G — Glama profile: realistic target

Bring the Glama profile to "all controllable items resolved" — the honest reading of "100%".

## Status (audited 2026-06-22, post-v0.0.6 ship)

## Achievable

- [ ] All three Card Badges = A (license, quality, maintenance). License + Maintenance confirmed A; **Quality grade not yet displayed** — pending Glama refresh after v0.0.6 ship. Refresh chase tracked in #31.
- [ ] Profile completion indicator hidden (= Glama treats profile as complete). **Currently at 25%** per most recent loop check.
- [

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/20) · 2026-06-21 · closed · 1 comment

### v0.0.6 Section E — Supply-chain compliance + governance

Per-package supply-chain compliance.

## Status (updated 2026-06-25, after the OpenSSF Best Practices Bronze badge ship)

## Tasks

- [x] SBOM (CycloneDX 1.6 + SPDX 2.3) on every release. Plus pip-licenses JSON manifest. Attached to every GitHub release via release.yml.
- [x] SLSA Build L3 + sigstore keyless attestations + PEP 740 PyPI attestations. Shipped via release.yml using `actions/attest-build-provenance@v3` + `pypa/gh-action-pypi-publish` with `attestations: true`.
- [x] OpenSSF Scorecar

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/18) · 2026-06-21 · closed · 1 comment

### v0.0.6 Section D — MCP server differentiation (umbrella)

Ship MCP features no competitor in finance/payments has yet. Synthesised from the 2026 MCP competitive-landscape research.

## Status (updated 2026-06-22, post-v0.0.7 D-series ship)

**6 of 7 D-series items shipped in v0.0.7.** Tool count grew from 11 (v0.0.6) to 19, plus 2 resources (incl. templated) and 4 guided prompts.

## Competitive context

- The only direct ISO 20022 competitor is **Pactus** (`deniskarlinsky/iso20022-mcp`): 9 generic tools, 2 GitHub stars, no Prompts/Resources/Sampling, 

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/17) · 2026-06-21 · closed · 1 comment

### feat: expose MCP resources and prompts, and add a validate_statement tool

## User story
**As an** author of AI agents, **I want to** consume MCP resources and prompt templates alongside a whole-statement validator, **so that** agents get richer guided context instead of only raw tools.

## Context
The MCP server (`camt053_mcp/server.py`) registers nine `@server.tool()` functions over FastMCP (`list_message_types`, `list_return_reasons`, `get_required_fields`, `get_input_schema`, `validate_records`, `validate_identifier`, `parse_statement`, `filter_entries`, `generate_

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/3) · 2026-06-17 · closed · 1 comment

### chore(glama): refresh Glama listing after v0.0.6 release

## Context

camt053-mcp v0.0.6 shipped (2026-06-22) with 13 tools (up from 11):

- Added: `check_cbpr_readiness` — Nov 14-16 2026 CBPR+ pre-flight
- Added: `get_cbpr_cutover_date` — returns canonical 2026-11-16

The Glama listing at <https://glama.ai/mcp/servers/sebastienrousseau/camt053-mcp> still reflects the v0.0.5 metadata and may need a re-scan to pick up the new tools, updated `glama.json` version (`0.0.6`), and the latest PyPI / GHCR availability.

## What to do

1. Force a Glama re-scan 

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/31) · 2026-06-22 · closed · 0 comments

### v0.0.6 Section F — Docs and examples coverage

Currently `camt053-mcp` has 1 example. To match the rest of the suite at v0.0.6, needs ~13 examples (one per `@server.tool()`) + test_examples coverage + quickstart.

## Status (audited 2026-06-22)

## Tasks

- [ ] One runnable example per `@server.tool()` decorator. **Current: 1 example (`examples/mcp_tools.py`). Target: ≥ 13 (one per registered tool).**
- [x] `interrogate --fail-under=100` gate enabled in `pyproject.toml`.
- [ ] `tests/test_examples.py` exercising each example end-to-end in CI

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/19) · 2026-06-21 · closed · 0 comments

### feat: paginate/stream large statement results and add a reversal-preview prompt

## User story
**As an** AI-agent author, **I want** the MCP tools to paginate large entry lists and a guided "reversal preview" prompt, **so that** agents handle big statements without overflowing context and get safe, previewable reversals.

## Context
The camt053-mcp server exposes 9 FastMCP `@server.tool()` tools wrapping `camt053.services`, including `list_entries` and `filter_entries`. Large statements can return entry lists that overflow an agent's context budget, and there is no guided wo

[Read the thread](https://github.com/sebastienrousseau/camt053-mcp/issues/4) · 2026-06-18 · closed · 0 comments

## Most recent

The remaining reports are on [the project's issue tracker](https://github.com/sebastienrousseau/camt053-mcp/issues).