add-mcp-tool
Skill0 starsChanged 54 days agoMITView on GitHub
Add or change a tool on the @codai/axiom-mcp stdio server — Zod input/output schemas, annotations, handler that never throws, registry mirror in spec/tools.json + README + docs/reference/mcp-tools.md, smoke test, changeset. Use when a user wants agents to be able to call a new AXIOM capability over MCP or a new CLI verb.
- Reads credentials
12 other projects use a version of this.
Adopted by
Most recently taken up by
- janusson/MSMCPtheir own version, first seen Oct 25, 2026
- skillist-io/skillisttheir own version, first seen Oct 11, 2026
- james5101/jobtracktheir own version, first seen Oct 11, 2026
- Locker-Room-Tools/synapsetheir own version, first seen Oct 11, 2026
- letehaha/moneymattertheir own version, first seen Oct 11, 2026
- openfootmanager/openfootmanagertheir own version, first seen Oct 8, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- openfootmanager/openfootmanager★ 1.2ksame name
- letehaha/moneymatter★ 221same name
- dylanroscover/Embody★ 213same name
- tacticlaunch/mcp-linear★ 147same name
- radimsem/remindb★ 125same name
- paulieb89/property-shared★ 16same name
- plumbkit/plumb★ 4same name
- james5101/jobtrack★ 2same name
- Locker-Room-Tools/synapse★ 2same name
- janusson/MSMCP★ 1same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- add-golden-fixtureSkill
- add-predicateSkill
- debug-apply-journalSkill
- release-axiomSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Every tool is one entry in the registry (packages/mcp/src/tools.ts or packages/mcp/src/tools/<name>.ts) with annotations + outputSchema, …
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Add an MCP tool
Every tool is one entry in the registry (packages/mcp/src/tools.ts or
packages/mcp/src/tools/<name>.ts) with annotations + outputSchema, and is
mirrored by hand into three documents. scripts/check-tool-parity.mjs fails CI
when any of the four disagree; .copilot-ripple.json reminds you while editing.
Steps
- Name it
axiom_<noun>_<verb>(snake_case, e.g.axiom_manifest_diff). Decide risk: reads →readOnlyHint: true; anything that writes a root →destructiveHint: true,idempotentHintas appropriate,openWorldHint: false. - Schemas — input and output as Zod built from
@codai/axiom-schematypes (import the schema, don't redefinePlan/ManifestBundle). Output must be small: digests, counts, paths,ERR_*codes. Bulk data goes behind anaxiom://…resource. - Handler — parse input with the Zod schema; on failure return a structured
error
{ code: "ERR_INVALID_INPUT", details }. Resolve every path through the roots allowlist (--root), neverprocess.cwd(). Call into@codai/axiom-plan/-checks/-apply; mapAxiomError→{ code, message, details }. Never throw out of the handler; log withconsole.erroronly. - Register the tool in the registry array; the server iterates it for
tools/list. If a CLI verb should exist too, add it inpackages/mcp/src/cli.ts(the only file allowed to use stdout /process.env). - Mirror (all three, same commit):
packages/mcp/spec/tools.json—{ name, riskClass, description }(this is what codai registers;apply-class =SENSITIVE, reads =READ).packages/mcp/README.md— tool table row.docs/reference/mcp-tools.md— tool table row (name, risk, purpose, input, output).
- Tests — extend the in-process smoke in
packages/mcp/src/*.test.ts:tools/listincludes the name with annotations + outputSchema; a malformed input returns anERR_*code; one happy path against a tmp root. Do not spawndist/cli.jsin unit tests. - Budgets — after
pnpm --filter @codai/axiom-mcp build, runnode scripts/run-guards.mjs bundle cold --strict: bin ≤ 950 KB, cold start p50 ≤ 250 ms. A new heavy dependency that breaks this needs a lazyimport(). - Changeset —
pnpm changeset→@codai/axiom-mcpminor. - Verify —
pnpm exec biome check packages/mcp,pnpm --filter @codai/axiom-mcp test,node scripts/run-guards.mjs tool-parity no-stdout no-shell— paste output.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.