@simplysf/simply-atlassian-mcp 0.4.1 → 0.4.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +79 -2
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -3,8 +3,8 @@
|
|
|
3
3
|
[](https://npmjs.com/@simplysf/simply-atlassian-mcp) [](https://raw.githubusercontent.com/SimplySF/simply-atlassian/main/LICENSE.txt)
|
|
4
4
|
|
|
5
5
|
A [Model Context Protocol](https://modelcontextprotocol.io/) server that gives an AI agent in
|
|
6
|
-
Claude Desktop, Claude Code, Cursor, VS Code, or any other MCP client the same Jira and
|
|
7
|
-
capabilities as the [`@simplysf/simply-atlassian`](../simply-atlassian) CLI: one tool per command,
|
|
6
|
+
Claude Desktop, Claude Code, Cursor, Gemini, VS Code, or any other MCP client the same Jira and
|
|
7
|
+
Confluence capabilities as the [`@simplysf/simply-atlassian`](../simply-atlassian) CLI: one tool per command,
|
|
8
8
|
calling the same [`@simplysf/simply-atlassian-core`](../simply-atlassian-core) library in-process.
|
|
9
9
|
The agent gets the CLI's credential handling, `dryRun` previews, read-only guard, credential
|
|
10
10
|
redaction, and error messages, and the same raw JSON the CLI prints with `--json`, without a
|
|
@@ -109,6 +109,83 @@ servers and whether each one connected.
|
|
|
109
109
|
Cursor reads `.cursor/mcp.json` in the project, or `~/.cursor/mcp.json` for every project, with
|
|
110
110
|
the same `mcpServers` shape as Claude Desktop.
|
|
111
111
|
|
|
112
|
+
### Gemini CLI
|
|
113
|
+
|
|
114
|
+
Gemini CLI reads `~/.gemini/settings.json` for every project, or `.gemini/settings.json` inside a
|
|
115
|
+
project, with the same `mcpServers` shape as Claude Desktop:
|
|
116
|
+
|
|
117
|
+
```json
|
|
118
|
+
{
|
|
119
|
+
"mcpServers": {
|
|
120
|
+
"simply-atlassian": {
|
|
121
|
+
"command": "simply-atlassian-mcp",
|
|
122
|
+
"args": ["--env-file", "/home/me/atlassian.env"]
|
|
123
|
+
}
|
|
124
|
+
}
|
|
125
|
+
}
|
|
126
|
+
```
|
|
127
|
+
|
|
128
|
+
`gemini mcp add` writes the same entry. `--scope user` puts it in the global file; the default
|
|
129
|
+
`project` scope writes `.gemini/settings.json`, and `-e` sets one variable on the entry:
|
|
130
|
+
|
|
131
|
+
```sh
|
|
132
|
+
gemini mcp add --scope user \
|
|
133
|
+
-e JIRA_URL=https://your-site.atlassian.net \
|
|
134
|
+
-e JIRA_USERNAME=you@example.com \
|
|
135
|
+
-e JIRA_API_TOKEN=... \
|
|
136
|
+
simply-atlassian simply-atlassian-mcp
|
|
137
|
+
```
|
|
138
|
+
|
|
139
|
+
Flags meant for the server itself, `--env-file` and `--allow-writes`, are easier to add by editing
|
|
140
|
+
`settings.json`, because `gemini mcp add` reads a leading-dash argument as one of its own options.
|
|
141
|
+
|
|
142
|
+
Values in `env` expand `$NAME` from the environment Gemini started in, which keeps the token out of
|
|
143
|
+
the settings file without an env file:
|
|
144
|
+
|
|
145
|
+
```json
|
|
146
|
+
{
|
|
147
|
+
"mcpServers": {
|
|
148
|
+
"simply-atlassian": {
|
|
149
|
+
"command": "npx",
|
|
150
|
+
"args": ["-y", "@simplysf/simply-atlassian-mcp"],
|
|
151
|
+
"env": {
|
|
152
|
+
"JIRA_URL": "https://your-site.atlassian.net",
|
|
153
|
+
"JIRA_USERNAME": "you@example.com",
|
|
154
|
+
"JIRA_API_TOKEN": "$JIRA_API_TOKEN"
|
|
155
|
+
}
|
|
156
|
+
}
|
|
157
|
+
}
|
|
158
|
+
}
|
|
159
|
+
```
|
|
160
|
+
|
|
161
|
+
Two other fields on an entry matter here. `trust: true` bypasses the per-call confirmation for
|
|
162
|
+
every tool on that server, so leave it off on any entry started with `--allow-writes` and let a
|
|
163
|
+
person approve each write. `includeTools` and `excludeTools` narrow what the model is shown, which
|
|
164
|
+
is a second way to express the split in [Let the agent write](#let-the-agent-write): a write entry
|
|
165
|
+
can register the write tools while holding back the destructive ones.
|
|
166
|
+
|
|
167
|
+
```json
|
|
168
|
+
{
|
|
169
|
+
"mcpServers": {
|
|
170
|
+
"simply-atlassian-write": {
|
|
171
|
+
"command": "simply-atlassian-mcp",
|
|
172
|
+
"args": ["--allow-writes", "--env-file", "/home/me/atlassian-write.env"],
|
|
173
|
+
"excludeTools": ["jira_issue_delete", "jira_issue_comment_delete", "confluence_page_delete"],
|
|
174
|
+
"trust": false
|
|
175
|
+
}
|
|
176
|
+
}
|
|
177
|
+
}
|
|
178
|
+
```
|
|
179
|
+
|
|
180
|
+
Inside a session, `/mcp` lists the configured servers, whether each connected, and the tools it
|
|
181
|
+
registered.
|
|
182
|
+
|
|
183
|
+
### Gemini Code Assist
|
|
184
|
+
|
|
185
|
+
Agent mode in the VS Code extension reads that same `~/.gemini/settings.json`, so an entry added
|
|
186
|
+
for Gemini CLI is already in place. In IntelliJ the file is `mcp.json` in the IDE's configuration
|
|
187
|
+
directory, holding the same `mcpServers` object.
|
|
188
|
+
|
|
112
189
|
### VS Code
|
|
113
190
|
|
|
114
191
|
VS Code reads `.vscode/mcp.json`, with a `servers` key and an explicit transport type:
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@simplysf/simply-atlassian-mcp",
|
|
3
3
|
"description": "Model Context Protocol server exposing Jira and Confluence to AI agents, built on @simplysf/simply-atlassian-core",
|
|
4
|
-
"version": "0.4.
|
|
4
|
+
"version": "0.4.2",
|
|
5
5
|
"author": "@ClayChipps",
|
|
6
6
|
"homepage": "https://github.com/SimplySF/simply-atlassian",
|
|
7
7
|
"bugs": "https://github.com/SimplySF/simply-atlassian/issues",
|
|
@@ -167,5 +167,5 @@
|
|
|
167
167
|
"service": true
|
|
168
168
|
}
|
|
169
169
|
},
|
|
170
|
-
"gitHead": "
|
|
170
|
+
"gitHead": "00dc34e673af42a05947595409e63cad9bd37d62"
|
|
171
171
|
}
|