# IBM/mcp-context-forge — health index 98/100 (Exceptional)

> Inspection of the public repository IBM/mcp-context-forge by inspect.software. It holds a health index of 98 out of 100, placing it in the Exceptional band. The index is a signal derived from publicly visible practice, not a warranty, a security audit, or an endorsement, and it is independent of payment.

- Repository: https://github.com/IBM/mcp-context-forge
- Report page: https://inspect.software/software/IBM/mcp-context-forge
- Full JSON report: https://inspect.software/api/repositories/IBM/mcp-context-forge/report
- Badge: https://raw.githubusercontent.com/inspect-software/badges/main/v1/i/IBM/mcp-context-forge.svg
- Inspected: 2026-08-03
- Methodology: metrics 2.3.1, report schema 0.30.0 (https://inspect.software/methodology.md)

## Category summary

| Category | Weight | Index | Band |
|---|---|---|---|
| Vitality | 21% | 96/100 | Exceptional |
| Community & Adoption | 17% | 91/100 | Excellent |
| Sustainability & Governance | 23% | 80/100 | Excellent |
| Engineering Quality | 19% | 100/100 | Exceptional |
| Security | 16% | 76/100 | Good |
| AI Readiness | 4% | 79/100 | Good |

The weighted overall 88 is calibrated to 98 on the published index scale (record calibration 2026-08-02).

## Repository facts

| Field | Value |
|---|---|
| Description | An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins. |
| Homepage | https://ibm.github.io/mcp-context-forge/ |
| Primary language | Python |
| License | Apache-2.0 |
| Stars | 4,178 |
| Forks | 789 |
| Created | 2025-05-08 |
| Last push | 2026-08-01 |
| Latest release | v1.0.6 |
| Commits (last year) | 2,223 |
| Bus factor | 3 |
| Topics | agents, ai, api-gateway, asyncio, authentication-middleware, devops, docker, fastapi, federation, gateway, generative-ai, jwt, kubernetes, llm-agents, mcp, model-context-protocol, observability, prompt-engineering, python, tools |

## Published packages

| Registry | Package | Latest | Monthly downloads |
|---|---|---|---|
| pypi | mcp-contextforge-gateway | 1.0.6 | — |

## Vitality — 96/100 (Exceptional)

Is the project alive — is code being written and are releases shipping? Weight: 21% of the overall index.

### Development activity — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Push recency | met | 36 / 36 | last push 1 days ago |
| Commit cadence | met | 36 / 36 | 52/52 weeks with commits |
| Commit volume | met | 18 / 18 | 2223 commits in the last year |
| OpenSSF Scorecard: Maintained | met | 10 / 10 | 30 commit(s) and 22 issue activity found in the last 90 days -- score normalized to 10 |

### Release discipline — 90/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ships releases | met | 27 / 27 | 23 releases published |
| Release recency | met | 36 / 36 | latest release 12 days ago |
| Release cadence | met | 27 / 27 | a release every ~17 days |
| OpenSSF Scorecard: Signed-Releases | not met | 0 / 10 | Project has not signed or included provenance with any releases. |

### Abandonment — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Project is still maintained | met | 100 / 100 | last human commit 2 days ago |

## Community & Adoption — 91/100 (Excellent)

Does the project have users, downloads, attention, and a welcoming setup for contributors? Weight: 17% of the overall index.

### Popularity & adoption — 91/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Stars | partial | 58.7 / 60 | 4,178 stars |
| Forks | partial | 24.1 / 25 | 789 forks |
| Watchers | partial | 8.4 / 15 | 34 watchers |

### Community health — 92/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 22.5 / 22.5 | — |
| License | met | 22.5 / 22.5 | recognized license (Apache-2.0) |
| CONTRIBUTING guide | met | 18 / 18 | — |
| Code of conduct | met | 13.5 / 13.5 | — |
| Issue template | not met | 0 / 7.2 | — |
| PR template | met | 6.3 / 6.3 | — |

## Sustainability & Governance — 80/100 (Excellent)

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep? Weight: 23% of the overall index.

### Maintainer resilience (bus factor) — 73/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Bus factor | partial | 36 / 54 | 3 contributor(s) cover half of all commits |
| Commit distribution | partial | 13.8 / 22.5 | top contributor authored 39% of commits |
| Contributor breadth | met | 13.5 / 13.5 | 100 contributors |
| OpenSSF Scorecard: Contributors | met | 10 / 10 | project has 13 contributing companies or organizations |

### Issue & PR responsiveness — 74/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Issue resolution | partial | 28.6 / 42 | 68% of issues closed |
| PR acceptance | partial | 24.4 / 30 | 2216/2729 decided PRs merged |
| Newcomer PR acceptance | partial | 8.7 / 13 | 4/6 first-time contributors' PRs merged in 30d |
| OpenSSF Scorecard: Code-Review | partial | 12 / 15 | Found 26/30 approved changesets -- score normalized to 8 |

### Ownership & stewardship — 80/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ownership backing | met | 30 / 30 | organization-owned |
| Verified domain | not met | 0 / 20 | — |
| Owner reach | met | 25 / 25 | 8,517 followers of IBM |
| Track record | met | 25 / 25 | 3925 public repos, account ~14 yr old |

### Package maintenance — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Published & resolvable | met | 25 / 25 | 1 package(s) on pypi |
| Publish recency | met | 35 / 35 | latest publish 12 days ago |
| Version history | met | 20 / 20 | 21 published versions |
| Not deprecated | met | 20 / 20 | active, not deprecated or yanked |

## Engineering Quality — 100/100 (Exceptional)

Are baseline engineering and documentation practices in place? Weight: 19% of the overall index.

### Engineering practices — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| CI workflows | met | 24 / 24 | 26 workflow(s) |
| Tests present | met | 24 / 24 | — |
| Linter config | met | 16 / 16 | .pylintrc, .ruff.toml, eslint.config.js, tox.ini |
| Pre-commit hooks | met | 9.6 / 9.6 | — |
| .editorconfig | met | 6.4 / 6.4 | — |
| OpenSSF Scorecard: CI-Tests | met | 20 / 20 | 26 out of 26 merged PRs checked by a CI test -- score normalized to 10 |

### Documentation — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 30 / 30 | — |
| Documentation directory | met | 25 / 25 | — |
| Documentation / homepage site | met | 15 / 15 | https://ibm.github.io/mcp-context-forge/ |
| Repository description | met | 10 / 10 | — |
| Topics | met | 10 / 10 | 20 topics |
| Wiki | met | 10 / 10 | — |

## Security — 76/100 (Good)

Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure? Weight: 16% of the overall index.

### Security posture — 70/100 (Good)

Excluded from scoring (no data or not applicable): Branch-Protection, Pinned-Dependencies. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Binary-Artifacts | met | 7.5 / 7.5 | no binaries found in the repo |
| Branch-Protection | excluded | 0 / 7.5 | internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md |
| CI-Tests | met | 2.5 / 2.5 | 26 out of 26 merged PRs checked by a CI test -- score normalized to 10 |
| CII-Best-Practices | not met | 0 / 2.5 | no effort to earn an OpenSSF best practices badge detected |
| Code-Review | partial | 6 / 7.5 | Found 26/30 approved changesets -- score normalized to 8 |
| Contributors | met | 2.5 / 2.5 | project has 13 contributing companies or organizations |
| Dangerous-Workflow | met | 10 / 10 | no dangerous workflow patterns detected |
| Dependency-Update-Tool | not met | 0 / 7.5 | no update tool detected |
| Fuzzing | met | 5 / 5 | project is fuzzed |
| License | met | 2.5 / 2.5 | license file detected |
| Maintained | met | 7.5 / 7.5 | 30 commit(s) and 22 issue activity found in the last 90 days -- score normalized to 10 |
| Packaging | met | 5 / 5 | packaging workflow detected |
| Pinned-Dependencies | excluded | 0 / 5 | internal error: internal error: invalid Dockerfile |
| SAST | not met | 0 / 5 | SAST tool is not run on all commits -- score normalized to 0 |
| Security-Policy | met | 5 / 5 | security policy file detected |
| Signed-Releases | not met | 0 / 7.5 | Project has not signed or included provenance with any releases. |
| Token-Permissions | partial | 6.8 / 7.5 | detected GitHub workflow tokens with excessive permissions |
| Vulnerabilities | partial | 4.5 / 7.5 | 4 existing vulnerabilities detected |

### Dependency advisories — 100/100 (Exceptional)

Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:mcp-contextforge-gateway@1.0.6 runtime dependency closure — what installing the published package pulls in — 91 packages. Reachability is not analyzed.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Direct dependencies free of known advisories | met | 35 / 35 | no direct dependency carries a known advisory |
| Indirect dependencies free of known advisories | met | 25 / 25 | no indirect dependency carries a known advisory |
| No advisories left outstanding | excluded | 0 / 40 | no advisory carries a publication date |

### Malicious dependencies — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| No dependency reported as a malicious package | met | 100 / 100 | no dependency is reported as a malicious package |

### High-Risk Jurisdiction Exposure — 100/100 (Exceptional)

Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Policy exposure multiplier | met | 100 / 100 | no confirmed policy-scope location match |

## AI Readiness — 79/100 (Good)

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight: agent tooling is a real maintenance signal, but its absence must never gate the top of the scale (calibration saturates at raw 91, so 100/100 remains reachable with AI Readiness at zero).

### Agent context & guidance — 85/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Agent instructions | met | 45 / 45 | AGENTS.md, CLAUDE.md, charts/AGENTS.md, docs/AGENTS.md, plugins/AGENTS.md, tests/AGENTS.md |
| Machine-readable docs (llms.txt) | not met | 0 / 15 | — |
| Legible commit history | met | 40 / 40 | 99 of 100 human commits state their intent (structured subject or explanatory body) |

### Verify loop (build / test / typecheck) — 82/100 (Excellent)

Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Pinned-Dependencies. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| One-command bootstrap | met | 18 / 18 | Makefile, charts/mcp-stack/Makefile, crates/mcp_runtime/Makefile, crates/wrapper/Makefile, docs/Makefile, mcp-servers/python/compliance_reference_server/Makefile, mcp-servers/python/data_analysis_server/Makefile, mcp-servers/python/graphviz_server/Makefile, mcp-servers/python/mcp-rss-search/Makefile, mcp-servers/python/mcp_eval_server/Makefile, mcp-servers/python/output_schema_test_server/Makefile, mcp-servers/python/python_sandbox_server/Makefile, mcp-servers/python/url_to_markdown_server/Makefile, mcp-servers/templates/go/{{cookiecutter.project_slug}}/Makefile, mcp-servers/templates/python/{{cookiecutter.project_slug}}/Makefile, plugins/external/cedar/Makefile, plugins/external/llmguard/Makefile, plugins/external/opa/Makefile, tests/client/Makefile, tests/load/Makefile, tests/performance/Makefile |
| Automated tests | met | 22 / 22 | — |
| Lint / format config | met | 11 / 11 | .pylintrc, .ruff.toml, eslint.config.js, tox.ini |
| Static type checking | met | 11 / 11 | mcpgateway/py.typed |
| Reproducible environment | met | 10 / 10 | devcontainer, Dockerfile, lockfile |
| Demonstrated agent practice | partial | 2 / 10 | 1 of the last 100 commits agent-authored or agent-credited |
| Automated maintenance | not met | 0 / 8 | no automated dependency updates observed |
| OpenSSF Scorecard: Pinned-Dependencies | excluded | 0 / 10 | internal error: internal error: invalid Dockerfile |

### Code legibility for models — 79/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Type-checkable code | partial | 27 / 45 | Python with type-check config (mcpgateway/py.typed) |
| Manageable file sizes | partial | 51.6 / 55 | 106/1737 source files over 60KB |

### Machine-readable interfaces — 60/100 (Moderate)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| API schema (OpenAPI/GraphQL/proto) | not met | 0 / 40 | — |
| MCP server | met | 20 / 20 | — |
| Runnable examples | met | 40 / 40 | examples |

## Collection warnings

- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- First-time contributor figures cover 12 of 19 authors (cap 12)

## What this report is

inspect.software measures public repositories against a single published, versioned methodology and reports the result as a 1–100 health index. Findings are signals derived from what is visible in public repository data — they are not a security audit, a warranty, or an endorsement, and no result depends on payment.

- Methodology, formulas and weights: https://inspect.software/methodology.md
- What a result does and does not claim: https://inspect.software/wiki/signals-not-warranties.md
- Rating bands: https://inspect.software/wiki/scoring-bands.md
- Corrections: https://inspect.software/contact.md
- Index of all documents: https://inspect.software/llms.txt